changelog and versions

Mobile Improvements for "Quick Filters" (2)

.gitignore

@@ -76,16 +76,11 @@ scripts/nuke
 /static/
 
 # Stored PDFs
-/media/documents/originals/*
-/media/documents/thumbnails/*
-
-/data/classification_model.pickle
-/data/db.sqlite3
-/data/index
-
+/media/
+/data/
 /paperless.conf
-/consume
-/export
+/consume/
+/export/
 /src-ui/.vscode
 
 # this is where the compiled frontend is moved to.

.travis.yml

@@ -1,5 +1,8 @@
 language: python
 
+dist: focal
+os: linux
+
 jobs:
   include:
     - name: "Paperless on Python 3.6"
@@ -33,7 +36,7 @@ jobs:
 
 before_install:
   - sudo apt-get update -qq
-  - sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr imagemagick ghostscript
+  - sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr imagemagick ghostscript optipng
 
 install:
   - pip install --upgrade pipenv

CONTRIBUTING.md

@@ -1,13 +1,30 @@
 # Contributing
 
-If you feel that somethings is not working, please submit an issue. You can also ask questions on the issue tracker by tagging your question with the question tag.
+There's still lots of things to be done, just have a look at that issue log. If you feel like conctributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome.
 
-Pull requests are welcome, however, I will be a little bit more strict about what goes into the code and what does not. If you want to make a big change, please ask me about it first.
+If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap in the readme.
 
 * When making additions to the project, consider if the majority of users will benefit from your change. If not, you're probably better of forking the project.
 * Also consider if your change will get in the way of other users. A good change is a change that enhances the experience of some users who want that change and does not affect users who do not care about the change.
 
-However:
+## Python
 
-* Bug fixes and are always welcome. Docker makes things easier, however, I alone cannot ensure that this runs on all platforms.
-* Improvements to the styling of the front-end are always welcome. I'm no expert in things UX, and simply copied one of the Bootstrap examples. I think it turned out rather good, but I just can't seem to get some things working properly.
+Use python 3.6 for development. Paperless supports python 3.6, 3.7 and 3.8.
+
+## Branches
+
+master always reflects the latest release.
+
+dev contains all changes that will be part of the next release. Use this branch to start making your changes.
+
+feature-X branches is for experimental stuff that will eventually be merged into dev, and then released as part of the next release.
+
+## Testing:
+
+I'm trying to get most of paperless tested, so please do the same for your code! I know its a hassle, but it makes sure that your code works now and will allow us to detect regressions easily.
+
+To test your code, execute `pytest` in the src/ directory. Executing that in the project root is no good. This also generates a html coverage report, which you can use to see if you missed anything important during testing.
+
+## More info:
+
+... is available in the documentation. https://paperless-ng.readthedocs.io/en/latest/extending.html

Pipfile

@@ -8,6 +8,9 @@ url = "https://www.piwheels.org/simple"
 verify_ssl = true
 name = "piwheels"
 
+[requires]
+python_version = "3.6"
+
 [packages]
 dateparser = "~=0.7.6"
 django = "~=3.1.3"
@@ -16,6 +19,7 @@ django-extensions = "*"
 django-filter = "~=2.4.0"
 django-q = "~=1.3.4"
 djangorestframework = "~=3.12.2"
+filelock = "*"
 fuzzywuzzy = "*"
 gunicorn = "*"
 imap-tools = "*"
@@ -23,7 +27,7 @@ langdetect = "*"
 pdftotext = "*"
 pathvalidate = "*"
 pillow = "*"
-pyocr = "~=0.7.2"
+pikepdf = "*"
 python-gnupg = "*"
 python-dotenv = "*"
 python-dateutil = "*"
@@ -35,6 +39,9 @@ scikit-learn="~=0.23.2"
 whitenoise = "~=5.2.0"
 watchdog = "*"
 whoosh="~=2.7.4"
+inotifyrecursive = "~=0.3.4"
+ocrmypdf = "*"
+tqdm = "*"
 
 [dev-packages]
 coveralls = "*"

Pipfile.lock

@@ -1,10 +1,12 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "ae2643b9cf0cf5741ae149fb6bc0c480de41329ce48e773eb4b5d760bc5e2244"
+            "sha256": "3d576f289958226a7583e4c471c7f8c11bff6933bf093185f623cfb381a92412"
         },
         "pipfile-spec": 6,
-        "requires": {},
+        "requires": {
+            "python_version": "3.6"
+        },
         "sources": [
             {
                 "name": "pypi",
@@ -37,10 +39,100 @@
         },
         "blessed": {
             "hashes": [
-                "sha256:7d4914079a6e8e14fbe080dcaf14dee596a088057cdc598561080e3266123b48",
-                "sha256:81125aa5b84cb9dfc09ff451886f64b4b923b75c5eaf51fde9d1c48a135eb797"
+                "sha256:0a74a8d3f0366db600d061273df77d44f0db07daade7bb7a4d49c8bc22ed9f74",
+                "sha256:580429e7e0c6f6a42ea81b0ae5a4993b6205c6ccbb635d034b4277af8175753e"
             ],
-            "version": "==1.17.11"
+            "version": "==1.17.12"
+        },
+        "cffi": {
+            "hashes": [
+                "sha256:00a1ba5e2e95684448de9b89888ccd02c98d512064b4cb987d48f4b40aa0421e",
+                "sha256:00e28066507bfc3fe865a31f325c8391a1ac2916219340f87dfad602c3e48e5d",
+                "sha256:045d792900a75e8b1e1b0ab6787dd733a8190ffcf80e8c8ceb2fb10a29ff238a",
+                "sha256:0638c3ae1a0edfb77c6765d487fee624d2b1ee1bdfeffc1f0b58c64d149e7eec",
+                "sha256:105abaf8a6075dc96c1fe5ae7aae073f4696f2905fde6aeada4c9d2926752362",
+                "sha256:155136b51fd733fa94e1c2ea5211dcd4c8879869008fc811648f16541bf99668",
+                "sha256:1a465cbe98a7fd391d47dce4b8f7e5b921e6cd805ef421d04f5f66ba8f06086c",
+                "sha256:1d2c4994f515e5b485fd6d3a73d05526aa0fcf248eb135996b088d25dfa1865b",
+                "sha256:23f318bf74b170c6e9adb390e8bd282457f6de46c19d03b52f3fd042b5e19654",
+                "sha256:2c24d61263f511551f740d1a065eb0212db1dbbbbd241db758f5244281590c06",
+                "sha256:51a8b381b16ddd370178a65360ebe15fbc1c71cf6f584613a7ea08bfad946698",
+                "sha256:594234691ac0e9b770aee9fcdb8fa02c22e43e5c619456efd0d6c2bf276f3eb2",
+                "sha256:5cf4be6c304ad0b6602f5c4e90e2f59b47653ac1ed9c662ed379fe48a8f26b0c",
+                "sha256:64081b3f8f6f3c3de6191ec89d7dc6c86a8a43911f7ecb422c60e90c70be41c7",
+                "sha256:6bc25fc545a6b3d57b5f8618e59fc13d3a3a68431e8ca5fd4c13241cd70d0009",
+                "sha256:798caa2a2384b1cbe8a2a139d80734c9db54f9cc155c99d7cc92441a23871c03",
+                "sha256:7c6b1dece89874d9541fc974917b631406233ea0440d0bdfbb8e03bf39a49b3b",
+                "sha256:840793c68105fe031f34d6a086eaea153a0cd5c491cde82a74b420edd0a2b909",
+                "sha256:8d6603078baf4e11edc4168a514c5ce5b3ba6e3e9c374298cb88437957960a53",
+                "sha256:9cc46bc107224ff5b6d04369e7c595acb700c3613ad7bcf2e2012f62ece80c35",
+                "sha256:9f7a31251289b2ab6d4012f6e83e58bc3b96bd151f5b5262467f4bb6b34a7c26",
+                "sha256:9ffb888f19d54a4d4dfd4b3f29bc2c16aa4972f1c2ab9c4ab09b8ab8685b9c2b",
+                "sha256:a5ed8c05548b54b998b9498753fb9cadbfd92ee88e884641377d8a8b291bcc01",
+                "sha256:a7711edca4dcef1a75257b50a2fbfe92a65187c47dab5a0f1b9b332c5919a3fb",
+                "sha256:af5c59122a011049aad5dd87424b8e65a80e4a6477419c0c1015f73fb5ea0293",
+                "sha256:b18e0a9ef57d2b41f5c68beefa32317d286c3d6ac0484efd10d6e07491bb95dd",
+                "sha256:b4e248d1087abf9f4c10f3c398896c87ce82a9856494a7155823eb45a892395d",
+                "sha256:ba4e9e0ae13fc41c6b23299545e5ef73055213e466bd107953e4a013a5ddd7e3",
+                "sha256:be8661bcee1bc2fc4b033a6ab65bd1f87ce5008492601695d0b9a4e820c3bde5",
+                "sha256:c6332685306b6417a91b1ff9fae889b3ba65c2292d64bd9245c093b1b284809d",
+                "sha256:d5ff0621c88ce83a28a10d2ce719b2ee85635e85c515f12bac99a95306da4b2e",
+                "sha256:d9efd8b7a3ef378dd61a1e77367f1924375befc2eba06168b6ebfa903a5e59ca",
+                "sha256:df5169c4396adc04f9b0a05f13c074df878b6052430e03f50e68adf3a57aa28d",
+                "sha256:ebb253464a5d0482b191274f1c8bf00e33f7e0b9c66405fbffc61ed2c839c775",
+                "sha256:ec80dc47f54e6e9a78181ce05feb71a0353854cc26999db963695f950b5fb375",
+                "sha256:f032b34669220030f905152045dfa27741ce1a6db3324a5bc0b96b6c7420c87b",
+                "sha256:f60567825f791c6f8a592f3c6e3bd93dd2934e3f9dac189308426bd76b00ef3b",
+                "sha256:f803eaa94c2fcda012c047e62bc7a51b0bdabda1cad7a92a522694ea2d76e49f"
+            ],
+            "version": "==1.14.4"
+        },
+        "chardet": {
+            "hashes": [
+                "sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
+                "sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
+            ],
+            "markers": "python_version >= '3.1'",
+            "version": "==3.0.4"
+        },
+        "coloredlogs": {
+            "hashes": [
+                "sha256:346f58aad6afd48444c2468618623638dadab76e4e70d5e10822676f2d32226a",
+                "sha256:a1fab193d2053aa6c0a97608c4342d031f1f93a3d1218432c59322441d31a505",
+                "sha256:b0c2124367d4f72bd739f48e1f61491b4baf145d6bda33b606b4a53cb3f96a97"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
+            "version": "==14.0"
+        },
+        "cryptography": {
+            "hashes": [
+                "sha256:07ca431b788249af92764e3be9a488aa1d39a0bc3be313d826bbec690417e538",
+                "sha256:13b88a0bd044b4eae1ef40e265d006e34dbcde0c2f1e15eb9896501b2d8f6c6f",
+                "sha256:257dab4f368fae15f378ea9a4d2799bf3696668062de0e9fa0ebb7a738a6917d",
+                "sha256:32434673d8505b42c0de4de86da8c1620651abd24afe91ae0335597683ed1b77",
+                "sha256:3cd75a683b15576cfc822c7c5742b3276e50b21a06672dc3a800a2d5da4ecd1b",
+                "sha256:4e7268a0ca14536fecfdf2b00297d4e407da904718658c1ff1961c713f90fd33",
+                "sha256:545a8550782dda68f8cdc75a6e3bf252017aa8f75f19f5a9ca940772fc0cb56e",
+                "sha256:55d0b896631412b6f0c7de56e12eb3e261ac347fbaa5d5e705291a9016e5f8cb",
+                "sha256:5849d59358547bf789ee7e0d7a9036b2d29e9a4ddf1ce5e06bb45634f995c53e",
+                "sha256:59f7d4cfea9ef12eb9b14b83d79b432162a0a24a91ddc15c2c9bf76a68d96f2b",
+                "sha256:6dc59630ecce8c1f558277ceb212c751d6730bd12c80ea96b4ac65637c4f55e7",
+                "sha256:7117319b44ed1842c617d0a452383a5a052ec6aa726dfbaffa8b94c910444297",
+                "sha256:75e8e6684cf0034f6bf2a97095cb95f81537b12b36a8fedf06e73050bb171c2d",
+                "sha256:7b8d9d8d3a9bd240f453342981f765346c87ade811519f98664519696f8e6ab7",
+                "sha256:a035a10686532b0587d58a606004aa20ad895c60c4d029afa245802347fab57b",
+                "sha256:a4e27ed0b2504195f855b52052eadcc9795c59909c9d84314c5408687f933fc7",
+                "sha256:a733671100cd26d816eed39507e585c156e4498293a907029969234e5e634bc4",
+                "sha256:a75f306a16d9f9afebfbedc41c8c2351d8e61e818ba6b4c40815e2b5740bb6b8",
+                "sha256:bd717aa029217b8ef94a7d21632a3bb5a4e7218a4513d2521c2a2fd63011e98b",
+                "sha256:d25cecbac20713a7c3bc544372d42d8eafa89799f492a43b79e1dfd650484851",
+                "sha256:d26a2557d8f9122f9bf445fc7034242f4375bd4e95ecda007667540270965b13",
+                "sha256:d3545829ab42a66b84a9aaabf216a4dce7f16dbc76eb69be5c302ed6b8f4a29b",
+                "sha256:d3d5e10be0cf2a12214ddee45c6bd203dab435e3d83b4560c03066eda600bfe3",
+                "sha256:efe15aca4f64f3a7ea0c09c87826490e50ed166ce67368a68f315ea0807a20df"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
+            "version": "==3.2.1"
         },
         "dateparser": {
             "hashes": [
@@ -52,11 +144,11 @@
         },
         "django": {
             "hashes": [
-                "sha256:14a4b7cd77297fba516fc0d92444cc2e2e388aa9de32d7a68d4a83d58f5a4927",
-                "sha256:14b87775ffedab2ef6299b73343d1b4b41e5d4e2aa58c6581f114dbec01e3f8f"
+                "sha256:5c866205f15e7a7123f1eec6ab939d22d5bde1416635cab259684af66d8e48a2",
+                "sha256:edb10b5c45e7e9c0fb1dc00b76ec7449aca258a39ffd613dbd078c51d19c9f03"
             ],
             "index": "pypi",
-            "version": "==3.1.3"
+            "version": "==3.1.4"
         },
         "django-cors-headers": {
             "hashes": [
@@ -68,11 +160,11 @@
         },
         "django-extensions": {
             "hashes": [
-                "sha256:6809c89ca952f0e08d4e0766bc0101dfaf508d7649aced1180c091d737046ea7",
-                "sha256:dc663652ac9460fd06580a973576820430c6d428720e874ae46b041fa63e0efa"
+                "sha256:7cd002495ff0a0e5eb6cdd6be759600905b4e4079232ea27618fc46bdd853651",
+                "sha256:c7f88625a53f631745d4f2bef9ec4dcb999ed59476393bdbbe99db8596778846"
             ],
             "index": "pypi",
-            "version": "==3.0.9"
+            "version": "==3.1.0"
         },
         "django-filter": {
             "hashes": [
@@ -105,6 +197,14 @@
             "index": "pypi",
             "version": "==3.12.2"
         },
+        "filelock": {
+            "hashes": [
+                "sha256:18d82244ee114f543149c66a6e0c14e9c4f8a1044b5cdaadd0f82159d6a6ff59",
+                "sha256:929b7d63ec5b7d6b71b0fa5ac14e030b3f70b75747cef1b10da9b879fef15836"
+            ],
+            "index": "pypi",
+            "version": "==3.0.12"
+        },
         "fuzzywuzzy": {
             "hashes": [
                 "sha256:45016e92264780e58972dca1b3d939ac864b78437422beecebb3095f8efd00e8",
@@ -121,13 +221,52 @@
             "index": "pypi",
             "version": "==20.0.4"
         },
+        "humanfriendly": {
+            "hashes": [
+                "sha256:175ffa628aa76da2c17369a5da5856084562cc66dfe7f82ae93ca3ef175277a6",
+                "sha256:3c9ab8d28e88e6cc998e41963357736dafd555ee5bb666b50e42f6ce28dd3e3d"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
+            "version": "==9.0"
+        },
         "imap-tools": {
             "hashes": [
-                "sha256:96e9a4ff6483462635737730a1df28e739faa71967b12a84f4363fb386542246",
-                "sha256:a3ee1827dc4ff185b259b33d0238b091a87d489f63ee59959fcc81716456c602"
+                "sha256:72bf46dc135b039a5d5b59f4e079242ac15eac02a30038e8cb2dec7b153cab65",
+                "sha256:75dc1c72dd76d9e577df26a1e0ec3a809b5eebce77678851458dcd2eae127ac9"
             ],
             "index": "pypi",
-            "version": "==0.32.0"
+            "version": "==0.33.0"
+        },
+        "img2pdf": {
+            "hashes": [
+                "sha256:57905015579b1026acf1605aa95859cd79b051fa1c35485573d165526fc9dbb5",
+                "sha256:eaee690ab8403dd1a9cb4db10afee41dd3e6c7ed63bdace02a0121f9feadb0c9"
+            ],
+            "version": "==0.4.0"
+        },
+        "importlib-metadata": {
+            "hashes": [
+                "sha256:6112e21359ef8f344e7178aa5b72dc6e62b38b0d008e6d3cb212c5b84df72013",
+                "sha256:b0c2d3b226157ae4517d9625decf63591461c66b3a808c2666d538946519d170"
+            ],
+            "markers": "python_version < '3.8'",
+            "version": "==3.1.1"
+        },
+        "inotify-simple": {
+            "hashes": [
+                "sha256:8440ffe49c4ae81a8df57c1ae1eb4b6bfa7acb830099bfb3e305b383005cc128",
+                "sha256:854f9ac752cc1fcff6ca34e9d3d875c9a94c9b7d6eb377f63be2d481a566c6ee"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==1.3.5"
+        },
+        "inotifyrecursive": {
+            "hashes": [
+                "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f",
+                "sha256:a2c450b317693e4538416f90eb1d7858506dafe6b8b885037bd2dd9ae2dafa1e"
+            ],
+            "index": "pypi",
+            "version": "==0.3.5"
         },
         "joblib": {
             "hashes": [
@@ -146,6 +285,51 @@
             "index": "pypi",
             "version": "==1.0.8"
         },
+        "lxml": {
+            "hashes": [
+                "sha256:0448576c148c129594d890265b1a83b9cd76fd1f0a6a04620753d9a6bcfd0a4d",
+                "sha256:127f76864468d6630e1b453d3ffbbd04b024c674f55cf0a30dc2595137892d37",
+                "sha256:1471cee35eba321827d7d53d104e7b8c593ea3ad376aa2df89533ce8e1b24a01",
+                "sha256:2363c35637d2d9d6f26f60a208819e7eafc4305ce39dc1d5005eccc4593331c2",
+                "sha256:2e5cc908fe43fe1aa299e58046ad66981131a66aea3129aac7770c37f590a644",
+                "sha256:2e6fd1b8acd005bd71e6c94f30c055594bbd0aa02ef51a22bbfa961ab63b2d75",
+                "sha256:366cb750140f221523fa062d641393092813b81e15d0e25d9f7c6025f910ee80",
+                "sha256:42ebca24ba2a21065fb546f3e6bd0c58c3fe9ac298f3a320147029a4850f51a2",
+                "sha256:4e751e77006da34643ab782e4a5cc21ea7b755551db202bc4d3a423b307db780",
+                "sha256:4fb85c447e288df535b17ebdebf0ec1cf3a3f1a8eba7e79169f4f37af43c6b98",
+                "sha256:50c348995b47b5a4e330362cf39fc503b4a43b14a91c34c83b955e1805c8e308",
+                "sha256:535332fe9d00c3cd455bd3dd7d4bacab86e2d564bdf7606079160fa6251caacf",
+                "sha256:535f067002b0fd1a4e5296a8f1bf88193080ff992a195e66964ef2a6cfec5388",
+                "sha256:5be4a2e212bb6aa045e37f7d48e3e1e4b6fd259882ed5a00786f82e8c37ce77d",
+                "sha256:60a20bfc3bd234d54d49c388950195d23a5583d4108e1a1d47c9eef8d8c042b3",
+                "sha256:648914abafe67f11be7d93c1a546068f8eff3c5fa938e1f94509e4a5d682b2d8",
+                "sha256:681d75e1a38a69f1e64ab82fe4b1ed3fd758717bed735fb9aeaa124143f051af",
+                "sha256:68a5d77e440df94011214b7db907ec8f19e439507a70c958f750c18d88f995d2",
+                "sha256:69a63f83e88138ab7642d8f61418cf3180a4d8cd13995df87725cb8b893e950e",
+                "sha256:6e4183800f16f3679076dfa8abf2db3083919d7e30764a069fb66b2b9eff9939",
+                "sha256:6fd8d5903c2e53f49e99359b063df27fdf7acb89a52b6a12494208bf61345a03",
+                "sha256:791394449e98243839fa822a637177dd42a95f4883ad3dec2a0ce6ac99fb0a9d",
+                "sha256:7a7669ff50f41225ca5d6ee0a1ec8413f3a0d8aa2b109f86d540887b7ec0d72a",
+                "sha256:7e9eac1e526386df7c70ef253b792a0a12dd86d833b1d329e038c7a235dfceb5",
+                "sha256:7ee8af0b9f7de635c61cdd5b8534b76c52cd03536f29f51151b377f76e214a1a",
+                "sha256:8246f30ca34dc712ab07e51dc34fea883c00b7ccb0e614651e49da2c49a30711",
+                "sha256:8c88b599e226994ad4db29d93bc149aa1aff3dc3a4355dd5757569ba78632bdf",
+                "sha256:91d6dace31b07ab47eeadd3f4384ded2f77b94b30446410cb2c3e660e047f7a7",
+                "sha256:923963e989ffbceaa210ac37afc9b906acebe945d2723e9679b643513837b089",
+                "sha256:94d55bd03d8671686e3f012577d9caa5421a07286dd351dfef64791cf7c6c505",
+                "sha256:97db258793d193c7b62d4e2586c6ed98d51086e93f9a3af2b2034af01450a74b",
+                "sha256:a9d6bc8642e2c67db33f1247a77c53476f3a166e09067c0474facb045756087f",
+                "sha256:cd11c7e8d21af997ee8079037fff88f16fda188a9776eb4b81c7e4c9c0a7d7fc",
+                "sha256:d8d3d4713f0c28bdc6c806a278d998546e8efc3498949e3ace6e117462ac0a5e",
+                "sha256:e0bfe9bb028974a481410432dbe1b182e8191d5d40382e5b8ff39cdd2e5c5931",
+                "sha256:e1dbb88a937126ab14d219a000728224702e0ec0fc7ceb7131c53606b7a76772",
+                "sha256:f4822c0660c3754f1a41a655e37cb4dbbc9be3d35b125a37fab6f82d47674ebc",
+                "sha256:f83d281bb2a6217cd806f4cf0ddded436790e66f393e124dfe9731f6b3fb9afe",
+                "sha256:fc37870d6716b137e80d19241d0e2cff7a7643b925dfa49b4c8ebd1295eb506e"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
+            "version": "==4.6.2"
+        },
         "numpy": {
             "hashes": [
                 "sha256:08308c38e44cc926bdfce99498b21eec1f848d24c302519e64203a8da99a97db",
@@ -187,6 +371,14 @@
             "markers": "python_version >= '3.6'",
             "version": "==1.19.4"
         },
+        "ocrmypdf": {
+            "hashes": [
+                "sha256:91e7394172cedb3be801a229dbd3d308fb5ae80cbc3a77879fa7954beea407b1",
+                "sha256:e550b8e884150accab7ea41f4a576b5844594cb5cbd6ed514fbf1206720343ad"
+            ],
+            "index": "pypi",
+            "version": "==11.3.4"
+        },
         "pathtools": {
             "hashes": [
                 "sha256:7c35c5421a39bb82e58018febd90e3b6e5db34c5443aaaf742b3f33d4655f1c0",
@@ -202,6 +394,14 @@
             "index": "pypi",
             "version": "==2.3.0"
         },
+        "pdfminer.six": {
+            "hashes": [
+                "sha256:b9aac0ebeafb21c08bf65f2039f4b2c5f78a3449d0a41df711d72445649e952a",
+                "sha256:d78877ba8d8bf957f3bb636c4f73f4f6f30f56c461993877ac22c39c20837509"
+            ],
+            "markers": "python_version >= '3.4'",
+            "version": "==20201018"
+        },
         "pdftotext": {
             "hashes": [
                 "sha256:98aeb8b07a4127e1a30223bd933ef080bbd29aa88f801717ca6c5618380b8aa6"
@@ -209,6 +409,33 @@
             "index": "pypi",
             "version": "==2.1.5"
         },
+        "pikepdf": {
+            "hashes": [
+                "sha256:0829bd5dacd73bb4a37e7575bae523f49603479755563c92ddb55c206700cab1",
+                "sha256:0d2b631077cd6af6e4d1b396208020705842610a6f13fab489d5f9c47916baa2",
+                "sha256:21c98af08fae4ac9fbcad02b613b6768a4ca300fda4cba867f4a4b6f73c2d04b",
+                "sha256:2240372fed30124ddc35b0c15a613f2b687a426ea2f150091e0a0c58cca7a495",
+                "sha256:2a97f5f1403e058d217d7f6861cf51fca200c5687bce0d052f5f2fa89b5bfa22",
+                "sha256:3faaefca0ae80d19891acec8b0dd5e6235f59f2206d82375eb80d090285e9557",
+                "sha256:48ef45b64882901c0d69af3b85d16a19bd0f3e95b43e614fefb53521d8caf36c",
+                "sha256:5212fe41f2323fc7356ba67caa39737fe13080562cff37bcbb74a8094076c8d0",
+                "sha256:56859c32170663c57bd0658189ce44e180533eebe813853446cd6413810be9eb",
+                "sha256:5f8fd1cb3478c5534222018aca24fbbd2bc74460c899bda988ec76722c13caa9",
+                "sha256:74300a32c41b3d578772f6933f23a88b19f74484185e71e5225ce2f7ea5aea78",
+                "sha256:8cbc946bdd217148f4a9c029fcea62f4ae0f67d5346de4c865f4718cd0ddc37f",
+                "sha256:9ceefd30076f732530cf84a1be2ecb2fa9931af932706ded760a6d37c73b96ad",
+                "sha256:ad69c170fda41b07a4c6b668a3128e7a759f50d9aebcfcde0ccff1358abe0423",
+                "sha256:b715fe182189fb6870fab5b0383bb2fb278c88c46eade346b0f4c1ed8818c09d",
+                "sha256:bb01ecf95083ffcb9ad542dc5342ccc1059e46f1395fd966629d36d9cc766b4a",
+                "sha256:bd6328547219cf48cefb4e0a1bc54442910594de1c5a5feae847d9ff3c629031",
+                "sha256:edb128379bb1dea76b5bdbdacf5657a6e4754bacc2049640762725590d8ed905",
+                "sha256:f8e687900557fcd4c51b4e72b9e337fdae9e2c81049d1d80b624bb2e88b5769d",
+                "sha256:fe0ca120e3347c851c34a91041d574f3c588d832023906d8ae18d66d042e8a52",
+                "sha256:fe8e0152672f24d8bfdecc725f97e9013f2de1b41849150959526ca3562bd3ef"
+            ],
+            "index": "pypi",
+            "version": "==2.2.0"
+        },
         "pillow": {
             "hashes": [
                 "sha256:006de60d7580d81f4a1a7e9f0173dc90a932e3905cc4d47ea909bc946302311a",
@@ -244,6 +471,14 @@
             "index": "pypi",
             "version": "==8.0.1"
         },
+        "pluggy": {
+            "hashes": [
+                "sha256:15b2acde666561e1298d71b523007ed7364de07029219b604cf808bfa1c765b0",
+                "sha256:966c145cd83c96502c3c3868f50408687b38434af77734af1e9ca461a4081d2d"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==0.13.1"
+        },
         "psycopg2-binary": {
             "hashes": [
                 "sha256:0deac2af1a587ae12836aa07970f5cb91964f05a7c6cdb69d8425ff4c15d4e2c",
@@ -287,13 +522,13 @@
             "index": "pypi",
             "version": "==2.8.6"
         },
-        "pyocr": {
+        "pycparser": {
             "hashes": [
-                "sha256:fa15adc7e1cf0d345a2990495fe125a947c6e09a60ddba0256a1c14b2e603179",
-                "sha256:fd602af17b6e21985669aadc058a95f343ff921e962ed4aa6520ded32e4d1301"
+                "sha256:2d475327684562c3a96cc71adf7dc8c4f0565175cf86b6d7a404ff4c771f15f0",
+                "sha256:7582ad22678f0fcd81102833f60ef8d0e57288b6b5fb00323d101be910e35705"
             ],
-            "index": "pypi",
-            "version": "==0.7.2"
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==2.20"
         },
         "python-dateutil": {
             "hashes": [
@@ -401,6 +636,53 @@
             ],
             "version": "==2020.11.13"
         },
+        "reportlab": {
+            "hashes": [
+                "sha256:0008b5baa39d7e3a8132c4b47ecae88d6858ad386518e754e5e7b8025ee4722b",
+                "sha256:0ad5a540c336941272fe161ef3a9830da3d4b3a65a195531cebd3cad5db58b2a",
+                "sha256:0c965a5691686d746f558ee1c52aa9c63a01a0e13cba61ffc661573948e32f61",
+                "sha256:0fd568fa5615ae99f76289c52ff230207852ee942d4934f6c893c93d2a79544e",
+                "sha256:1117d905a3404c696869c7aabec9454b43ed6acbbc73f9256c6fcea23e7ae93e",
+                "sha256:1ea7c388e91ad9d823655ad6a13751ff67e8a0e7cf4065cf051b4c931cdd9450",
+                "sha256:26c0ee8f62652cc7fcdc47a1cb3b34775a4d625738025c1a7edb8718bda5a315",
+                "sha256:368c5b3fc3d5a541cb9dcacefa563fdb445365f517e3cbf64b4326631d1cf13c",
+                "sha256:451d42fdcdd7d84587d6d9c8f5d9a7d0e997305efb606705063ca1fe8bcca551",
+                "sha256:47394acba4da8e56ef8e55d8eb483b868521696ba49ab0f0fcf8a1a4a5ac6e49",
+                "sha256:51b16e297f7b937fc530dd151e4b38f1d305b01c9aa10657bc32a5d2901b8ad7",
+                "sha256:51c0cdcf606ded0a7b4b50050400f25125ea797fbfc3c817135993b38f8b764e",
+                "sha256:55c672c579618843e0fd00140fb71f1ffebc4f1c542ac385c4f4999f2f5398d9",
+                "sha256:5c34a96ecfbf595caf16178a06abcd26a5f8720e01fe1285d4c97333382cfaeb",
+                "sha256:61aa89a00754b18c4f2956b8bff831f1fd3affef6476dc63462d92211941605e",
+                "sha256:62234d29c97279917903e4587faf240a5dea4617be250db55386ff268eb5a7c5",
+                "sha256:670f2a8dcc23bf798c39b95c64bf76ee387549b962f76783670821978a226663",
+                "sha256:69387f171f6c7b55109caa6d061b17a18f2f9e724a0212c07cd692aeb369dd19",
+                "sha256:6c5c8871b659f7c2975382d7b61f3c182701fa9eb62cf649c3c73ba8fc5e2595",
+                "sha256:80139ceb3a568f5be908094f1701fd05391b71425e8b69aaed0d30db647ca2aa",
+                "sha256:80661a76d0019b5e2c315ccd3bc7093d754067d6142b36a3a0ec4f416073d23b",
+                "sha256:85a2236f324ae336da7f4b183fa99bed261bcc00ac1255ee91a504e68b086d00",
+                "sha256:89a3acd98bd4478d6bbc5cb32e0665ea546c98bff8b58d5e1014659daa6ef75a",
+                "sha256:8a39119fcab146bde41fd1c6d148f9ee1e2cca10c6f9c2b7eb4dd710a3a2c6ac",
+                "sha256:9c31c2526401da6cc92018f68483f2aac0a731cb98435445ea4b72d46b438c84",
+                "sha256:9e8ae1c3b8a1697147c5c97f00d66ab1c54d88c4615b0cdd9b1a667d7baf3eb7",
+                "sha256:a479c38ab2b997ce05d3bef906783ac20cf4cb224a154e80c9018c5e4d943a35",
+                "sha256:a79aab8d069543d5085d58260f18705a08acd92a4501a41261913fddc2137d46",
+                "sha256:b0a8314383de853599ca531dfe55eaa49bb8d6b0bb663b2f8479b7a0f3385ea2",
+                "sha256:b3d9926e64bd8008007b2d9819d7b30179b069ce95431d5060f71afc36885389",
+                "sha256:c2a9a77ce4f25ffb52d705be82a9f41b47f6b0da23870ebc3587709e7242da30",
+                "sha256:c578dd0799f70fb577474cd383f035c6e1057e4fe837278113f9cfa6eee4b076",
+                "sha256:c5abd9d0023ad20030524ab0d5fa39d77aed025519b1fa426304ab2dd0328b89",
+                "sha256:ced96125525ba21311e9512adf391170b9e149f89e27e45b06ff07b70f97a0b2",
+                "sha256:d692fb88d6ef5e75242b00009b54953a0425eaa8bd3a36db9db8b396785e1f57",
+                "sha256:d70c2104286459658e61388af9eee838b612986bd8a36e1d21ba36152983ac15",
+                "sha256:de47c65c10ac6f0d2addb28f1b1657b1c707aca014d09d01b3b728cf19e8f791",
+                "sha256:e6e7592527791841db0820a72c6afae52655a05b0b6d4df184fd2bafe82ee1ee",
+                "sha256:e8a7e95ee6ea5566291b59ede5b9fadce809dca43ebfbfe11e3ff3d6492c6f0e",
+                "sha256:f041759138b3a95508c4281b3db3bf9bb28636d84c554272a58a5ca7c9f9bbf4",
+                "sha256:f39c7fc1fa2e4a1d9747a3effd70731a9d0e9eb5738247fa089c059eff19d43e",
+                "sha256:f65ac89ee0ba569f5279360eae08783f7f2e95c9810a9846c957fbd5950f4896"
+            ],
+            "version": "==3.5.56"
+        },
         "scikit-learn": {
             "hashes": [
                 "sha256:090bbf144fd5823c1f2efa3e1a9bf180295b24294ca8f478e75b40ed54f8036e",
@@ -464,6 +746,13 @@
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
             "version": "==1.15.0"
         },
+        "sortedcontainers": {
+            "hashes": [
+                "sha256:37257a32add0a3ee490bb170b599e93095eed89a55da91fa9f48753ea12fd73f",
+                "sha256:59cc937650cf60d677c16775597c89a960658a09cf7c1a668f86e1e4464b10a1"
+            ],
+            "version": "==2.3.0"
+        },
         "sqlparse": {
             "hashes": [
                 "sha256:017cde379adbd6a1f15a61873f43e8274179378e95ef3fede90b5aa64d304ed0",
@@ -480,6 +769,14 @@
             "markers": "python_version >= '3.5'",
             "version": "==2.1.0"
         },
+        "tqdm": {
+            "hashes": [
+                "sha256:38b658a3e4ecf9b4f6f8ff75ca16221ae3378b2e175d846b6b33ea3a20852cf5",
+                "sha256:d4f413aecb61c9779888c64ddf0c62910ad56dcbe857d8922bb505d4dbff0df1"
+            ],
+            "index": "pypi",
+            "version": "==4.54.1"
+        },
         "tzlocal": {
             "hashes": [
                 "sha256:643c97c5294aedc737780a49d9df30889321cbe1204eac2c2ec6134035a92e44",
@@ -489,11 +786,11 @@
         },
         "watchdog": {
             "hashes": [
-                "sha256:034c85530b647486e8c8477410fe79476511282658f2ce496f97106d9e5acfb8",
-                "sha256:4214e1379d128b0588021880ccaf40317ee156d4603ac388b9adcf29165e0c04"
+                "sha256:3caefdcc8f06a57fdc5ef2d22aa7c0bfda4f55e71a0bee74cbf3176d97536ef3",
+                "sha256:e38bffc89b15bafe2a131f0e1c74924cf07dcec020c2e0a26cccd208831fcd43"
             ],
             "index": "pypi",
-            "version": "==0.10.3"
+            "version": "==0.10.4"
         },
         "wcwidth": {
             "hashes": [
@@ -518,6 +815,14 @@
             ],
             "index": "pypi",
             "version": "==2.7.4"
+        },
+        "zipp": {
+            "hashes": [
+                "sha256:102c24ef8f171fd729d46599845e95c7ab894a4cf45f5de11a44cc7444fb1108",
+                "sha256:ed5eee1974372595f9e416cc7bbeeb12335201d8081ca8a0743c954d4446e5cb"
+            ],
+            "markers": "python_version >= '3.6'",
+            "version": "==3.4.0"
         }
     },
     "develop": {
@@ -561,16 +866,17 @@
         },
         "certifi": {
             "hashes": [
-                "sha256:1f422849db327d534e3d0c5f02a263458c3955ec0aae4ff09b95f195c59f4edd",
-                "sha256:f05def092c44fbf25834a51509ef6e631dc19765ab8a57b4e7ab85531f0a9cf4"
+                "sha256:1a4995114262bffbc2413b159f2a1a480c969de6e6eb13ee966d470af86af59c",
+                "sha256:719a74fb9e33b9bd44cc7f3a8d94bc35e4049deebe19ba7d8e108280cfd59830"
             ],
-            "version": "==2020.11.8"
+            "version": "==2020.12.5"
         },
         "chardet": {
             "hashes": [
                 "sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
                 "sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
             ],
+            "markers": "python_version >= '3.1'",
             "version": "==3.0.4"
         },
         "coverage": {
@@ -663,17 +969,18 @@
         },
         "faker": {
             "hashes": [
-                "sha256:3f5d379e4b5ce92a8afe3c2ce59d7c43886370dd3bf9495a936b91888debfc81",
-                "sha256:8c0e8a06acef4b9312902e2ce18becabe62badd3a6632180bd0680c6ee111473"
+                "sha256:1fcb415562ee6e2395b041e85fa6901d4708d30b84d54015226fa754ed0822c3",
+                "sha256:e8beccb398ee9b8cc1a91d9295121d66512b6753b4846eb1e7370545d46b3311"
             ],
-            "markers": "python_version >= '3.5'",
-            "version": "==4.17.0"
+            "markers": "python_version >= '3.6'",
+            "version": "==5.0.1"
         },
         "filelock": {
             "hashes": [
                 "sha256:18d82244ee114f543149c66a6e0c14e9c4f8a1044b5cdaadd0f82159d6a6ff59",
                 "sha256:929b7d63ec5b7d6b71b0fa5ac14e030b3f70b75747cef1b10da9b879fef15836"
             ],
+            "index": "pypi",
             "version": "==3.0.12"
         },
         "idna": {
@@ -693,6 +1000,22 @@
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
             "version": "==1.2.0"
         },
+        "importlib-metadata": {
+            "hashes": [
+                "sha256:6112e21359ef8f344e7178aa5b72dc6e62b38b0d008e6d3cb212c5b84df72013",
+                "sha256:b0c2d3b226157ae4517d9625decf63591461c66b3a808c2666d538946519d170"
+            ],
+            "markers": "python_version < '3.8'",
+            "version": "==3.1.1"
+        },
+        "importlib-resources": {
+            "hashes": [
+                "sha256:7b51f0106c8ec564b1bef3d9c588bc694ce2b92125bbb6278f4f2f5b54ec3592",
+                "sha256:a3d34a8464ce1d5d7c92b0ea4e921e696d86f2aa212e684451cb1482c8d84ed5"
+            ],
+            "markers": "python_version < '3.7'",
+            "version": "==3.3.0"
+        },
         "iniconfig": {
             "hashes": [
                 "sha256:011e24c64b7f47f6ebd835bb12a743f2fbe9a26d4cecaa7f53bc4f35ee9da8b3",
@@ -754,11 +1077,11 @@
         },
         "packaging": {
             "hashes": [
-                "sha256:4357f74f47b9c12db93624a82154e9b120fa8293699949152b22065d556079f8",
-                "sha256:998416ba6962ae7fbd6596850b80e17859a5753ba17c32284f67bfff33784181"
+                "sha256:05af3bb85d320377db281cf254ab050e1a7ebcbf5410685a9a407e18a1f81236",
+                "sha256:eb41423378682dadb7166144a4926e443093863024de508ca5c9737d6bc08376"
             ],
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
-            "version": "==20.4"
+            "version": "==20.7"
         },
         "pluggy": {
             "hashes": [
@@ -786,11 +1109,11 @@
         },
         "pygments": {
             "hashes": [
-                "sha256:381985fcc551eb9d37c52088a32914e00517e57f4a21609f48141ba08e193fa0",
-                "sha256:88a0bbcd659fcb9573703957c6b9cff9fab7295e6e76db54c9d00ae42df32773"
+                "sha256:ccf3acacf3782cbed4a989426012f1c535c9a90d3a7fc3f16d231b9372d2b716",
+                "sha256:f275b6c0909e5dafd2d6269a656aa90fa58ebf4a74f8fcf9053195d226b24a08"
             ],
             "markers": "python_version >= '3.5'",
-            "version": "==2.7.2"
+            "version": "==2.7.3"
         },
         "pyparsing": {
             "hashes": [
@@ -999,11 +1322,19 @@
         },
         "virtualenv": {
             "hashes": [
-                "sha256:b0011228208944ce71052987437d3843e05690b2f23d1c7da4263fde104c97a2",
-                "sha256:b8d6110f493af256a40d65e29846c69340a947669eec8ce784fcf3dd3af28380"
+                "sha256:54b05fc737ea9c9ee9f8340f579e5da5b09fb64fd010ab5757eb90268616907c",
+                "sha256:b7a8ec323ee02fb2312f098b6b4c9de99559b462775bc8fe3627a73706603c1b"
             ],
             "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
-            "version": "==20.1.0"
+            "version": "==20.2.2"
+        },
+        "zipp": {
+            "hashes": [
+                "sha256:102c24ef8f171fd729d46599845e95c7ab894a4cf45f5de11a44cc7444fb1108",
+                "sha256:ed5eee1974372595f9e416cc7bbeeb12335201d8081ca8a0743c954d4446e5cb"
+            ],
+            "markers": "python_version >= '3.6'",
+            "version": "==3.4.0"
         }
     }
 }

README.md

@@ -7,7 +7,7 @@
 
 [Paperless](https://github.com/the-paperless-project/paperless) is an application by Daniel Quinn and others that indexes your scanned documents and allows you to easily search for documents and store metadata alongside your documents.
 
-Paperless-ng is a fork of the original project, adding a new interface and many other changes under the hood. For a detailed list of changes, see below.
+Paperless-ng is a fork of the original project, adding a new interface and many other changes under the hood. For a detailed list of changes, have a look at the changelog in the documentation.
 
 This project is still in development and some things may not work as expected.
 
@@ -15,70 +15,103 @@ This project is still in development and some things may not work as expected.
 
 Paperless does not control your scanner, it only helps you deal with what your scanner produces.
 
-1. Buy a document scanner that can write to a place on your network.  If you need some inspiration, have a look at the [scanner recommendations](https://paperless-ng.readthedocs.io/en/latest/scanners.html) page.
-2. Set it up to "scan to FTP" or something similar. It should be able to push scanned images to a server without you having to do anything.  Of course if your scanner doesn't know how to automatically upload the file somewhere, you can always do that manually. Paperless doesn't care how the documents get into its local consumption directory.
-3. Have the target server run the Paperless consumption script to OCR the file and index it into a local database.
-4. Use the web frontend to sift through the database and find what you want.
-5. Download the PDF you need/want via the web interface and do whatever you like with it.  You can even print it and send it as if it's the original. In most cases, no one will care or notice.
+1. Buy a document scanner that can write to a place on your network.  If you need some inspiration, have a look at the [scanner recommendations](https://paperless-ng.readthedocs.io/en/latest/scanners.html) page. Set it up to "scan to FTP" or something similar. It should be able to push scanned images to a server without you having to do anything.  Of course if your scanner doesn't know how to automatically upload the file somewhere, you can always do that manually. Paperless doesn't care how the documents get into its local consumption directory.
 
-# Why Paperless-ng?
+	- Alternatively, you can use any of the mobile scanning apps out there. We have an app that allows you to share documents with paperless, if you're on Android. See the section on affiliated projects.
 
-I wanted to make big changes to the project that will impact the way it is used by its users greatly. Among the users who currently use paperless in production there are probably many that don't want these changes right away. I also wanted to have more control over what goes into the code and what does not. Therefore, paperless-ng was created. NG stands for both Angular (the framework used for the Frontend) and next-gen. Publishing this project under a different name also avoids confusion between paperless and paperless-ng.
+2. Wait for paperless to process your files. OCR is expensive, and depending on the power of your machine, this might take a bit of time.
+3. Use the web frontend to sift through the database and find what you want.
+4. Download the PDF you need/want via the web interface and do whatever you like with it.  You can even print it and send it as if it's the original. In most cases, no one will care or notice.
 
-The gist of the changes is the following:
+Here's what you get:
 
-* New front end. This will eventually be mobile friendly as well.
-* New full text search.
-* New email processing.
+![Dashboard](https://github.com/jonaswinkler/paperless-ng/raw/master/docs/_static/screenshots/dashboard.png)
+
+# Features
+
+* Performs OCR on your documents, adds selectable text to image only documents and adds tags, correspondents and document types to your documents.
+* Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and can be configured freely.
+* Single page application front end. Should be pretty snappy. Will be mobile friendly in the future.
+	* Includes a dashboard that shows basic statistics and has document upload.
+	* Filtering by tags, correspondents, types, and more.
+	* Customizable views can be saved and displayed on the dashboard.
+	* Full text search with auto completion, scored results and query highlighting allows you to quickly find what you need.
+* Email processing: Paperless adds documents from your email accounts.
+	* Configure multiple accounts and filters for each account.
+	* When adding documents from mails, paperless can move these mails to a new folder, mark them as read, flag them or delete them.
 * Machine learning powered document matching.
-* Code cleanup in many, MANY areas.
+	* Paperless learns from your documents and will be able to automatically assign tags, correspondents and types to documents once you've stored a few documents in paperless.
+* A task processor that processes documents in parallel and also tells you when something goes wrong. On modern multi core systems, consumption is blazing fast.
+* Code cleanup in many, MANY areas. Some of the code from OG paperless was just overly complicated.
+* More tests, more stability.
 
 If you want to see some screenshots of paperless-ng in action, [some are available in the documentation](https://paperless-ng.readthedocs.io/en/latest/screenshots.html).
 
-For a complete list of changes, check out the [changelog](https://paperless-ng.readthedocs.io/en/latest/changelog.html)
+For a complete list of changes from paperless, check out the [changelog](https://paperless-ng.readthedocs.io/en/latest/changelog.html)
 
-## Planned
+# Roadmap for 1.0
 
-These features will make it into the application at some point, sorted by priority.
+- Make the front end nice (except mobile).
+- Test coverage at 90%.
+- Fix whatever bugs I and you find.
 
+## Roadmap for versions beyond 1.0
+
+These are things that I want to add to paperless eventually. They are sorted by priority.
+
+- **Bulk editing**. Add/remove metadata from multiple documents at once.
 - **More search.** The search backend is incredibly versatile and customizable. Searching is the most important feature of this project and thus, I want to implement things like:
   - Group and limit search results by correspondent, show “more from this” links in the results.
   - Ability to search for “Similar documents” in the search results
-  - Provide corrections for mispelled queries
-- **More robust consumer** that shows its progress on the web page.
+- **Nested tags**. Organize tags in a hierarchical structure. This will combine the benefits of folders and tags in one coherent system.
+- **An interactive consumer** that shows its progress for documents it processes on the web page.
+	- With live updates ans websockets. This already works on a dev branch, but requires a lot of new dependencies, which I'm not particular happy about.
+	- Notifications when a document was added with buttons to open the new document right away.
 - **Arbitrary tag colors**. Allow the selection of any color with a color picker.
 
 ## On the chopping block.
 
-- **GnuPG encrypion.** Since its disabled by default and the website allows transparent access to encrypted documents anyway, this doesn’t really provide any benefit over having the application stored on an encrypted file system.
+- **GnuPG encrypion.** [Here's a note about encryption in paperless](https://paperless-ng.readthedocs.io/en/latest/administration.html#managing-encryption). The gist of it is that I don't see which attacks this implementation protects against. It gives a false sense of security to users who don't care about how it works.
 
 # Getting started
 
-The recommended way to deploy paperless is docker-compose. Grab the latest release to get started. the dockerfiles archive contains just the docker files which will pull the image from docker hub. The source archive contains everything you need to build the docker image yourself.
+The recommended way to deploy paperless is docker-compose. Don't clone the repository, grab the latest release to get started instead. The dockerfiles archive contains just the docker files which will pull the image from docker hub. The source archive contains everything you need to build the docker image yourself (i.e. if you want to run on Raspberry Pi).
 
 Read the [documentation](https://paperless-ng.readthedocs.io/en/latest/setup.html#installation) on how to get started.
 
-Alternatively, you can install the dependencies and setup apache and a database server yourself. Details for that will be available in the documentation at some point.
+Alternatively, you can install the dependencies and setup apache and a database server yourself. The documenation has a step by step guide on how to do it.
 
 # Migrating to paperless-ng
 
-Read the section about [migration](https://paperless-ng.readthedocs.io/en/latest/setup.html#migration-to-paperless-ng) in the documentation.
+Read the section about [migration](https://paperless-ng.readthedocs.io/en/latest/setup.html#migration-to-paperless-ng) in the documentation. Its also entirely possible to go back to paperless by reverting the database migrations.
 
 # Documentation
 
 The documentation for Paperless-ng is available on [ReadTheDocs](https://paperless-ng.readthedocs.io/).
 
+# Suggestions? Questions? Something not working?
+
+Please open an issue and start a discussion about it!
+
+## Feel like helping out?
+
+There's still lots of things to be done, just have a look at that issue log. If you feel like contributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome. The documentation has some basic information on how to get started.
+
+If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap above.
+
 # Affiliated Projects
 
 Paperless has been around a while now, and people are starting to build stuff on top of it.  If you're one of those people, we can add your project to this list:
 
-* [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless.
+* [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless. Updated to work with paperless-ng.
+* [Paperless Share](https://github.com/qcasey/paperless_share). Share any files from your Android application with paperless. Very simple, but works with all of the mobile scanning apps out there that allow you to share scanned documents.
+
+These projects also exist, but their status and compatibility with paperless-ng is unknown.
+
 * [Paperless Desktop](https://github.com/thomasbrueggemann/paperless-desktop): A desktop UI for your Paperless installation.  Runs on Mac, Linux, and Windows.
 * [ansible-role-paperless](https://github.com/ovv/ansible-role-paperless): An easy way to get Paperless running via Ansible.
 * [paperless-cli](https://github.com/stgarf/paperless-cli): A golang command line binary to interact with a Paperless instance.
 
-Compatibility with Paperless-ng is unknown.
-
 # Important Note
 
 Document scanners are typically used to scan sensitive documents.  Things like your social insurance number, tax records, invoices, etc.  Everything is stored in the clear without encryption by default (it needs to be searchable, so if someone has ideas on how to do that on encrypted data, I'm all ears).  This means that Paperless should never be run on an untrusted host.  Instead, I recommend that if you do want to use it, run it locally on a server in your own home.

docker/docker-compose.env

@@ -32,8 +32,3 @@
 # The default language to use for OCR. Set this to the language most of your
 # documents are written in.
 #PAPERLESS_OCR_LANGUAGE=eng
-
-# By default Paperless does not OCR a document if the text can be retrieved from
-# the document directly. Set to true to always OCR documents. (i.e., if you
-# know that some of your documents have faulty/bad OCR data)
-#PAPERLESS_OCR_ALWAYS=true

docker/docker-entrypoint.sh

@@ -23,8 +23,14 @@ wait_for_postgres() {
 	echo "Waiting for PostgreSQL to start..."
 
 	host="${PAPERLESS_DBHOST}"
+	port="${PAPERLESS_DBPORT}"
 
-	while !</dev/tcp/$host/5432 ;
+	if [[ -z $port ]] ;
+	then
+		port="5432"
+	fi
+
+	while !</dev/tcp/$host/$port ;
 	do
 
 		if [ $attempt_num -eq $max_attempts ]
@@ -113,13 +119,13 @@ install_languages() {
     done
 }
 
-initialize
-
 # Install additional languages if specified
 if [[ ! -z "$PAPERLESS_OCR_LANGUAGES"  ]]; then
 		install_languages "$PAPERLESS_OCR_LANGUAGES"
 fi
 
+initialize
+
 if [[ "$1" != "/"* ]]; then
 	exec sudo -HEu paperless python3 manage.py "$@"
 else

docker/hub/docker-compose.postgres.yml

@@ -15,7 +15,7 @@ services:
       POSTGRES_PASSWORD: paperless
 
   webserver:
-    image: jonaswinkler/paperless-ng:0.9.2
+    image: jonaswinkler/paperless-ng:0.9.8
     restart: always
     depends_on:
       - db

docker/hub/docker-compose.sqlite.yml

@@ -5,7 +5,7 @@ services:
     restart: always
 
   webserver:
-    image: jonaswinkler/paperless-ng:0.9.2
+    image: jonaswinkler/paperless-ng:0.9.8
     restart: always
     depends_on:
       - broker

docker/local/Dockerfile

@@ -11,12 +11,18 @@ RUN apt-get update \
 		curl \
 		ghostscript \
 		gnupg \
+		icc-profiles-free \
 		imagemagick \
 		libatlas-base-dev \
+		liblept5 \
 		libmagic-dev \
 		libpoppler-cpp-dev \
 		libpq-dev \
+		libqpdf-dev \
+		libxml2 \
 		optipng \
+		pngquant \
+		qpdf \
 		sudo \
 		tesseract-ocr \
 		tesseract-ocr-eng \
@@ -26,9 +32,10 @@ RUN apt-get update \
 		tesseract-ocr-spa \
 		tzdata \
 		unpaper \
+		zlib1g \
 	&& pip3 install --upgrade supervisor setuptools \
 	&& pip install --no-cache-dir -r requirements.txt \
-	&& apt-get -y purge build-essential \
+	&& apt-get -y purge build-essential libqpdf-dev \
 	&& apt-get -y autoremove --purge \
 	&& rm -rf /var/lib/apt/lists/* \
 	&& mkdir /var/log/supervisord /var/run/supervisord

docs/administration.rst

@@ -30,7 +30,7 @@ Options available to docker installations:
     Paperless uses 3 volumes:
 
     *   ``paperless_media``: This is where your documents are stored.
-    *   ``paperless_data``: This is where auxilliary data is stored. This
+    *   ``paperless_data``: This is where auxillary data is stored. This
         folder also contains the SQLite database, if you use it.
     *   ``paperless_pgdata``: Exists only if you use PostgreSQL and contains
         the database.
@@ -69,7 +69,7 @@ First of all, ensure that paperless is stopped.
 
 After that, :ref:`make a backup <administration-backup>`.
 
-A.  If you used the docker-compose file, simply download the files of the new release,
+A.  If you used the dockerfiles archive, simply download the files of the new release,
     adjust the settings in the files (i.e., the path to your consumption directory),
     and replace your existing docker-compose files. Then start paperless as usual,
     which will pull the new image, and update your database, if necessary:
@@ -109,7 +109,7 @@ B.  If you built the image yourself, grab the new archive and replace your curre
 .. hint::
 
     You can usually keep your ``docker-compose.env`` file, since this file will
-    never include mandantory configuration options. However, it is worth checking
+    never include mandatory configuration options. However, it is worth checking
     out the new version of this file, since it might have new recommendations
     on what to configure.
 
@@ -119,27 +119,30 @@ Updating paperless without docker
 
 After grabbing the new release and unpacking the contents, do the following:
 
-1.  Update python requirements. Paperless uses
-    `Pipenv`_ for managing dependencies:
+1.  Update dependencies. New paperless version may require additional
+    dependencies. The dependencies required are listed in the section about 
+    :ref:`bare metal installations <setup-bare_metal>`.
+
+2.  Update python requirements. If you use Pipenv, this is done with the following steps.
 
     .. code:: shell-session
 
         $ pip install --upgrade pipenv
         $ cd /path/to/paperless
-        $ pipenv install
         $ pipenv clean
+        $ pipenv install
 
     This creates a new virtual environment (or uses your existing environment)
     and installs all dependencies into it.
 
-2.  Collect static files.
+3.  Collect static files.
 
     .. code:: shell-session
 
         $ cd src
         $ pipenv run python3 manage.py collectstatic --clear
     
-3.  Migrate the database.
+4.  Migrate the database.
 
     .. code:: shell-session
 
@@ -153,14 +156,14 @@ Management utilities
 Paperless comes with some management commands that perform various maintenance
 tasks on your paperless instance. You can invoke these commands either by
 
-.. code:: bash
+.. code:: shell-session
 
     $ cd /path/to/paperless
     $ docker-compose run --rm webserver <command> <arguments>
 
 or
 
-.. code:: bash
+.. code:: shell-session
 
     $ cd /path/to/paperless/src
     $ pipenv run python manage.py <command> <arguments>
@@ -247,12 +250,12 @@ your already processed documents.
 
 When multiple document types or correspondents match a single document,
 the retagger won't assign these to the document. Specify ``--use-first``
-to override this behaviour and just use the first correspondent or type
+to override this behavior and just use the first correspondent or type
 it finds. This option does not apply to tags, since any amount of tags
 can be applied to a document.
 
 Finally, ``-f`` specifies that you wish to overwrite already assigned
-correspondents, types and/or tags. The default behaviour is to not
+correspondents, types and/or tags. The default behavior is to not
 assign correspondents and types to documents that have this data already
 assigned. ``-f`` works differently for tags: By default, only additional tags get
 added to documents, no tags will be removed. With ``-f``, tags that don't
@@ -274,6 +277,7 @@ management command:
 
 This command takes no arguments.
 
+.. _`administration-index`:
 
 Managing the document search index
 ==================================
@@ -332,6 +336,42 @@ command:
 
 The command takes no arguments and processes all your mail accounts and rules.
 
+.. _utilities-archiver:
+
+Creating archived documents
+===========================
+
+Paperless stores archived PDF/A documents alongside your original documents.
+These archived documents will also contain selectable text for image-only
+originals.
+These documents are derived from the originals, which are always stored
+unmodified. If coming from an earlier version of paperless, your documents
+won't have archived versions.
+
+This command creates PDF/A documents for your documents.
+
+.. code::
+
+    document_archiver --overwrite --document <id>
+
+This command will only attempt to create archived documents when no archived
+document exists yet, unless ``--overwrite`` is specified. If ``--document <id>``
+is specified, the archiver will only process that document.
+
+.. note::
+
+    This command essentially performs OCR on all your documents again,
+    according to your settings. If you run this with ``PAPERLESS_OCR_MODE=redo``,
+    it will potentially run for a very long time. You can cancel the command
+    at any time, since this command will skip already archived versions the next time
+    it is run.
+
+.. note::
+
+    Some documents will cause errors and cannot be converted into PDF/A documents,
+    such as encrypted PDF documents. The archiver will skip over these documents
+    each time it sees them.
+
 .. _utilities-encyption:
 
 Managing encryption
@@ -341,7 +381,7 @@ Documents can be stored in Paperless using GnuPG encryption.
 
 .. danger::
 
-    Encryption is depreceated since paperless-ng 0.9 and doesn't really provide any
+    Encryption is deprecated since paperless-ng 0.9 and doesn't really provide any
     additional security, since you have to store the passphrase in a configuration
     file on the same system as the encrypted documents for paperless to work.
     Furthermore, the entire text content of the documents is stored plain in the
@@ -353,39 +393,23 @@ Documents can be stored in Paperless using GnuPG encryption.
     Consider running paperless on an encrypted filesystem instead, which will then
     at least provide security against physical hardware theft.
 
-.. code::
-
-    change_storage_type [--passphrase PASSPHRASE] {gpg,unencrypted} {gpg,unencrypted}
-
-    positional arguments:
-      {gpg,unencrypted}     The state you want to change your documents from
-      {gpg,unencrypted}     The state you want to change your documents to
-
-    optional arguments:
-      --passphrase PASSPHRASE
 
 Enabling encryption
 -------------------
 
-Basic usage to enable encryption of your document store (**USE A MORE SECURE PASSPHRASE**):
-
-(Note: If ``PAPERLESS_PASSPHRASE`` isn't set already, you need to specify it here)
-
-.. code::
-
-    change_storage_type [--passphrase SECR3TP4SSPHRA$E] unencrypted gpg
+Enabling encryption is no longer supported.
 
 
 Disabling encryption
 --------------------
 
-Basic usage to enable encryption of your document store:
+Basic usage to disable encryption of your document store:
 
-(Note: Again, if ``PAPERLESS_PASSPHRASE`` isn't set already, you need to specify it here)
+(Note: If ``PAPERLESS_PASSPHRASE`` isn't set already, you need to specify it here)
 
 .. code::
 
-    change_storage_type [--passphrase SECR3TP4SSPHRA$E] gpg unencrypted
+    decrypt_documents [--passphrase SECR3TP4SSPHRA$E]
 
 
 .. _Pipenv: https://pipenv.pypa.io/en/latest/

docs/advanced_usage.rst

@@ -84,6 +84,8 @@ to the filename.
    PAPERLESS_FILENAME_PARSE_TRANSFORMS=[{"pattern":"^([a-z]+)_(\\d{8})_(\\d{6})_([0-9]+)\\.", "repl":"\\2\\3Z - \\4 - \\1."}, {"pattern":"^([a-z]+)_([0-9]+)\\.", "repl":" - \\2 - \\1."}]
 
 
+.. _advanced-matching:
+
 Matching tags, correspondents and document types
 ################################################
 
@@ -145,7 +147,9 @@ America are tagged with the tag "bofa_123" and the matching algorithm of this
 tag is set to *Auto*, this neural network will examine your documents and
 automatically learn when to assign this tag.
 
-There are a couple caveats you need to keep in mind when using this feature:
+Paperless tries to hide much of the involved complexity with this approach.
+However, there are a couple caveats you need to keep in mind when using this
+feature:
 
 * Changes to your documents are not immediately reflected by the matching
   algorithm. The neural network needs to be *trained* on your documents after
@@ -165,6 +169,11 @@ There are a couple caveats you need to keep in mind when using this feature:
   has the correspondent "Very obscure web shop I bought something five years
   ago", it will probably not assign this correspondent automatically if you buy
   something from them again. The more documents, the better.
+* Paperless also needs a reasonable amount of negative examples to decide when
+  not to assign a certain tag, correspondent or type. This will usually be the
+  case as you start filling up paperless with documents. Example: If all your
+  documents are either from "Webshop" and "Bank", paperless will assign one of
+  these correspondents to ANY new document, if both are set to automatic matching.
 
 Hooking into the consumption process
 ####################################
@@ -253,11 +262,11 @@ By default, paperless stores your documents in the media directory and renames t
 using the identifier which it has assigned to each document. You will end up getting
 files like ``0000123.pdf`` in your media directory. This isn't necessarily a bad
 thing, because you normally don't have to access these files manually. However, if
-you wish to name your files differently, you can do that by adjustng the
-``PAPERLESS_FILENAME_FORMAT`` settings variable.
+you wish to name your files differently, you can do that by adjusting the
+``PAPERLESS_FILENAME_FORMAT`` configuration option.
 
-This variable allows you to configure the filename (folders are allowed!) using
-placeholders. For example, setting
+This variable allows you to configure the filename (folders are allowed) using
+placeholders. For example, configuring this to
 
 .. code:: bash
 
@@ -268,17 +277,16 @@ will create a directory structure as follows:
 .. code::
 
     2019/
-      my_bank/
-        statement-january-0000001.pdf
-        statement-february-0000002.pdf
+      My bank/
+        Statement January.pdf
+        Statement February.pdf
     2020/
-      my_bank/
-        statement-january-0000003.pdf
-      shoe_store/
-        my_new_shoes-0000004.pdf
-
-Paperless appends the unique identifier of each document to the filename. This
-avoides filename clashes.
+      My bank/
+        Statement January.pdf
+        Letter.pdf
+        Letter_01.pdf
+      Shoe store/
+        My new shoes.pdf
 
 .. danger::
 
@@ -289,6 +297,8 @@ avoides filename clashes.
 Paperless provides the following placeholders withing filenames:
 
 * ``{correspondent}``: The name of the correspondent, or "none".
+* ``{document_type}``: The name of the document type, or "none".
+* ``{tag_list}``: A comma separated list of all tags assigned to the document.
 * ``{title}``: The title of the document.
 * ``{created}``: The full date and time the document was created.
 * ``{created_year}``: Year created only.
@@ -298,10 +308,15 @@ Paperless provides the following placeholders withing filenames:
 * ``{added_year}``: Year added only.
 * ``{added_month}``: Month added only (number 1-12).
 * ``{added_day}``: Day added only (number 1-31).
-* ``{tags}``: I don't know how this works. Look at the source.
 
-Paperless will convert all values for the placeholders into values which are safe
-for use in filenames.
+
+Paperless will try to conserve the information from your database as much as possible.
+However, some characters that you can use in document titles and correspondent names (such
+as ``: \ /`` and a couple more) are not allowed in filenames and will be replaced with dashes.
+
+If paperless detects that two documents share the same filename, paperless will automatically
+append ``_01``, ``_02``, etc to the filename. This happens if all the placeholders in a filename
+evaluate to the same value.
 
 .. hint::
 

docs/api.rst

@@ -13,23 +13,55 @@ available filters and ordering fields.
 
 The API provides 5 main endpoints:
 
+*   ``/api/documents/``: Full CRUD support, except POSTing new documents. See below.
 *   ``/api/correspondents/``: Full CRUD support.
 *   ``/api/document_types/``: Full CRUD support.
-*   ``/api/documents/``: Full CRUD support, except POSTing new documents. See below.
 *   ``/api/logs/``: Read-Only.
 *   ``/api/tags/``: Full CRUD support.
 
-All of these endpoints except for the logging endpoint 
+All of these endpoints except for the logging endpoint
 allow you to fetch, edit and delete individual objects
 by appending their primary key to the path, for example ``/api/documents/454/``.
 
+The objects served by the document endpoint contain the following fields:
+
+*   ``id``: ID of the document. Read-only.
+*   ``title``: Title of the document.
+*   ``content``: Plain text content of the document.
+*   ``tags``: List of IDs of tags assigned to this document, or empty list.
+*   ``document_type``: Document type of this document, or null.
+*   ``correspondent``:  Correspondent of this document or null.
+*   ``created``: The date at which this document was created.
+*   ``modified``: The date at which this document was last edited in paperless. Read-only.
+*   ``added``: The date at which this document was added to paperless. Read-only.
+*   ``archive_serial_number``: The identifier of this document in a physical document archive.
+*   ``original_file_name``: Verbose filename of the original document. Read-only.
+*   ``archived_file_name``: Verbose filename of the archived document. Read-only. Null if no archived document is available.
+
+
+Downloading documents
+#####################
+
 In addition to that, the document endpoint offers these additional actions on
 individual documents:
 
-*   ``/api/documents/<pk>/download/``: Download the original document.
-*   ``/api/documents/<pk>/thumb/``: Download the PNG thumbnail of a document.
-*   ``/api/documents/<pk>/preview/``: Display the original document inline,
+*   ``/api/documents/<pk>/download/``: Download the document.
+*   ``/api/documents/<pk>/preview/``: Display the document inline,
     without downloading it.
+*   ``/api/documents/<pk>/thumb/``: Download the PNG thumbnail of a document.
+
+Paperless generates archived PDF/A documents from consumed files and stores both
+the original files as well as the archived files. By default, the endpoints
+for previews and downloads serve the archived file, if it is available.
+Otherwise, the original file is served.
+Some document cannot be archived.
+
+The endpoints correctly serve the response header fields ``Content-Disposition``
+and ``Content-Type`` to indicate the filename for download and the type of content of
+the document.
+
+In order to download or preview the original document when an archied document is available,
+supply the query parameter ``original=true``.
 
 .. hint::
 
@@ -38,6 +70,80 @@ individual documents:
     are in place. However, if you use these old URLs to access documents, you
     should update your app or script to use the new URLs.
 
+
+Getting document metadata
+#########################
+
+The api also has an endpoint to retrieve read-only metadata about specific documents. this
+information is not served along with the document objects, since it requires reading
+files and would therefore slow down document lists considerably.
+
+Access the metadata of a document with an ID ``id`` at ``/api/documents/<id>/metadata/``.
+
+The endpoint reports the following data:
+
+*   ``original_checksum``: MD5 checksum of the original document.
+*   ``original_size``: Size of the original document, in bytes.
+*   ``original_mime_type``: Mime type of the original document.
+*   ``media_filename``: Current filename of the document, under which it is stored inside the media directory.
+*   ``has_archive_version``: True, if this document is archived, false otherwise.
+*   ``original_metadata``: A list of metadata associated with the original document. See below.
+*   ``archive_checksum``: MD5 checksum of the archived document, or null.
+*   ``archive_size``: Size of the archived document in bytes, or null.
+*   ``archive_metadata``: Metadata associated with the archived document, or null. See below.
+
+File metadata is reported as a list of objects in the following form:
+
+.. code:: json
+
+    [
+        {
+            "namespace": "http://ns.adobe.com/pdf/1.3/",
+            "prefix": "pdf",
+            "key": "Producer",
+            "value": "SparklePDF, Fancy edition"
+        },
+    ]
+
+``namespace`` and ``prefix`` can be null. The actual metadata reported depends on the file type and the metadata
+available in that specific document. Paperless only reports PDF metadata at this point.
+
+Authorization
+#############
+
+The REST api provides three different forms of authentication.
+
+1.  Basic authentication
+
+    Authorize by providing a HTTP header in the form
+
+    .. code::
+
+        Authorization: Basic <credentials>
+
+    where ``credentials`` is a base64-encoded string of ``<username>:<password>``
+
+2.  Session authentication
+
+    When you're logged into paperless in your browser, you're automatically
+    logged into the API as well and don't need to provide any authorization
+    headers.
+
+3.  Token authentication
+
+    Paperless also offers an endpoint to acquire authentication tokens.
+
+    POST a username and password as a form or json string to ``/api/token/``
+    and paperless will respond with a token, if the login data is correct.
+    This token can be used to authenticate other requests with the
+    following HTTP header:
+
+    .. code::
+
+        Authorization: Token <token>
+
+    Tokens can be managed and revoked in the paperless admin.
+
 Searching for documents
 #######################
 
@@ -65,8 +171,9 @@ Result list object returned by the endpoint:
         "count": 1,
         "page": 1,
         "page_count": 1,
+        "corrected_query": "",
         "results": [
-            
+
         ]
     }
 
@@ -75,6 +182,8 @@ Result list object returned by the endpoint:
     the page you requested, if you requested a page that is behind
     the last page. In that case, the last page is returned.
 *   ``page_count``: The total number of pages.
+*   ``corrected_query``: Corrected version of the query string. Can be null.
+    If not null, can be used verbatim to start a new query.
 *   ``results``: A list of result objects on the current page.
 
 Result object:
@@ -84,17 +193,17 @@ Result object:
     {
         "id": 1,
         "highlights": [
-            
+
         ],
         "score": 6.34234,
         "rank": 23,
         "document": {
-            
+
         }
     }
 
 *   ``id``: the primary key of the found document
-*   ``highlights``: an object containing parseable highlights for the result.
+*   ``highlights``: an object containing parsable highlights for the result.
     See below.
 *   ``score``: The score assigned to the document. A higher score indicates a
     better match with the query. Search results are sorted descending by score.
@@ -121,7 +230,7 @@ Each fragment contains a list of strings, and some of them are marked as a highl
             {"text": " fragment with a highlight."}
         ]
     ]
-    
+
 
 
 When ``term`` is present within a string, the word within ``text`` should be highlighted.
@@ -166,8 +275,17 @@ The API provides a special endpoint for file uploads:
 
 POST a multipart form to this endpoint, where the form field ``document`` contains
 the document that you want to upload to paperless. The filename is sanitized and
-then used to store the document in the consumption folder, where the consumer will
-detect the document and process it as any other document.
+then used to store the document in a temporary directory, and the consumer will
+be instructed to consume the document from there.
 
-The endpoint will immediately return "OK." if the document was stored in the
-consumption directory.
+The endpoint supports the following optional form fields:
+
+*   ``title``: Specify a title that the consumer should use for the document.
+*   ``correspondent``: Specify the ID of a correspondent that the consumer should use for the document.
+*   ``document_type``: Similar to correspondent.
+*   ``tags``: Similar to correspondent. Specify this multiple times to have multiple tags added
+    to the document.
+
+The endpoint will immediately return "OK" if the document consumption process
+was started successfully. No additional status information about the consumption
+process itself is available, since that happens in a different process.

docs/changelog.rst

@@ -5,6 +5,195 @@
 Changelog
 *********
 
+
+paperless-ng 0.9.8
+##################
+
+This release addresses two severe issues with the previous release.
+
+* The delete buttons for document types, correspondents and tags were not working.
+* The document section in the admin was causing internal server errors (500).
+
+
+paperless-ng 0.9.7
+##################
+
+
+* Front end
+
+  * Thanks to the hard work of `Michael Shamoon`_, paperless now comes with a much more streamlined UI for
+    filtering documents.
+  
+  * `Michael Shamoon`_ replaced the document preview with another component. This should fix compatibility with Safari browsers.
+
+  * Added buttons to the management pages to quickly show all documents with one specific tag, correspondent, or title.
+  
+  * Paperless now stores your saved views on the server and associates them with your user account. 
+    This means that you can access your views on multiple devices and have separate views for different users.
+    You will have to recreate your views.
+
+  * The GitHub and documentation links now open in new tabs/windows. Thanks to `rYR79435`_.
+
+  * Paperless now generates default saved view names when saving views with certain filter rules.
+
+  * Added a small version indicator to the front end.
+
+* Other additions and changes
+
+  * The new filename format field ``{tag_list}`` inserts a list of tags into the filename, separated by comma.
+  * The ``document_retagger`` no longer removes inbox tags or tags without matching rules.
+  * The new configuration option ``PAPERLESS_COOKIE_PREFIX`` allows you to run multiple instances of paperless on different ports.
+    This option enables you to be logged in into multiple instances by specifying different cookie names for each instance.
+
+* Fixes
+  
+  * Sometimes paperless would assign dates in the future to newly consumed documents.
+  * The filename format fields ``{created_month}`` and ``{created_day}`` now use a leading zero for single digit values.
+  * The filename format field ``{tags}`` can no longer be used without arguments.
+  * Paperless was not able to consume many images (especially images from mobile scanners) due to missing DPI information.
+    Paperless now assumes A4 paper size for PDF generation if no DPI information is present.
+  * Documents with empty titles could not be opened from the table view due to the link being empty.
+  * Fixed an issue with filenames containing special characters such as ``:`` not being accepted for upload.
+  * Fixed issues with thumbnail generation for plain text files.
+
+
+paperless-ng 0.9.6
+##################
+
+This release focusses primarily on many small issues with the UI.
+
+* Front end
+
+  * Paperless now has proper window titles.
+  * Fixed an issue with the small cards when more than 7 tags were used.
+  * Navigation of the "Show all" links adjusted. They navigate to the saved view now, if available in the sidebar.
+  * Some indication on the document lists that a filter is active was added.
+  * There's a new filter to filter for documents that do *not* have a certain tag.
+  * The file upload box now shows upload progress.
+  * The document edit page was reorganized.
+  * The document edit page shows various information about a document.
+  * An issue with the height of the preview was fixed.
+  * Table issues with too long document titles fixed.
+
+* API
+
+  * The API now serves file names with documents.
+  * The API now serves various metadata about documents.
+  * API documentation updated.
+
+* Other
+
+  * Fixed an issue with the docker image when a non-standard PostgreSQL port was used.
+  * The docker image was trying check for installed languages before actually installing them.
+  * ``FILENAME_FORMAT`` placeholder for document types.
+  * The filename formatter is now less restrictive with file names and tries to
+    conserve the original correspondents, types and titles as much as possible.
+  * The filename formatter does not include the document ID in filenames anymore. It will
+    rather append ``_01``, ``_02``, etc when it detects duplicate filenames.
+
+.. note::
+
+  The changes to the filename format will apply to newly added documents and changed documents.
+  If you want all files to reflect these changes, execute the ``document_renamer`` management
+  command.
+
+
+paperless-ng 0.9.5
+##################
+
+This release concludes the big changes I wanted to get rolled into paperless. The next releases before 1.0 will
+focus on fixing issues, primarily.
+
+* OCR
+
+  * Paperless now uses `OCRmyPDF <https://github.com/jbarlow83/OCRmyPDF>`_ to perform OCR on documents.
+    It still uses tesseract under the hood, but the PDF parser of Paperless has changed considerably and
+    will behave different for some douments.
+  * OCRmyPDF creates archived PDF/A documents with embedded text that can be selected in the front end.
+  * Paperless stores archived versions of documents alongside with the originals. The originals can be
+    accessed on the document edit page. If available, a dropdown menu will appear next to the download button.
+  * Many of the configuration options regarding OCR have changed. See :ref:`configuration-ocr` for details.
+  * Paperless no longer guesses the language of your documents. It always uses the language that you
+    specified with ``PAPERLESS_OCR_LANGUAGE``. Be sure to set this to the language the majority of your
+    documents are in. Multiple languages can be specified, but that requires more CPU time.
+  * The management command :ref:`document_archiver <utilities-archiver>` can be used to create archived versions for already
+    existing documents.
+
+* Tags from consumption folder.
+
+  * Thanks to `jayme-github`_, paperless now consumes files from sub folders in the consumption folder and is able to assign tags
+    based on the sub folders a document was found in. This can be configured with ``PAPERLESS_CONSUMER_RECURSIVE`` and
+    ``PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS``.
+
+* API
+
+  * The API now offers token authentication.
+  * The endpoint for uploading documents now supports specifying custom titles, correspondents, tags and types.
+    This can be used by clients to override the default behavior of paperless. See :ref:`api-file_uploads`.
+  * The document endpoint of API now serves documents in this form:
+
+    * correspondents, document types and tags are referenced by their ID in the fields ``correspondent``, ``document_type`` and ``tags``. The ``*_id`` versions are gone. These fields are read/write.
+    * paperless does not serve nested tags, correspondents or types anymore.
+
+* Front end
+
+  * Paperless does some basic caching of correspondents, tags and types and will only request them from the server when necessary or when entirely reloading the page.
+  * Document list fetching is about 10%-30% faster now, especially when lots of tags/correspondents are present.
+  * Some minor improvements to the front end, such as document count in the document list, better highlighting of the current page, and improvements to the filter behavior.
+
+* Fixes:
+
+  * A bug with the generation of filenames for files with unsupported types caused the exporter and
+    document saving to crash.
+  * Mail handling no longer exits entirely when encountering errors. It will skip the account/rule/message on which the error occured.
+  * Assigning correspondents from mail sender names failed for very long names. Paperless no longer assigns correspondents in these cases.
+
+paperless-ng 0.9.4
+##################
+
+* Searching:
+
+  * Paperless now supports searching by tags, types and dates and correspondents. In order to have this applied to your
+    existing documents, you need to perform a ``document_index reindex`` management command
+    (see :ref:`administration-index`)
+    that adds the data to the search index. You only need to do this once, since the schema of the search index changed.
+    Paperless keeps the index updated after that whenever something changes.
+  * Paperless now has spelling corrections ("Did you mean") for miss-typed queries.
+  * The documentation contains :ref:`information about the query syntax <basic-searching>`.
+
+* Front end:
+
+  * Clickable tags, correspondents and types allow quick filtering for related documents.
+  * Saved views are now editable.
+  * Preview documents directly in the browser.
+  * Navigation from the dashboard to saved views.
+
+* Fixes:
+
+  * A severe error when trying to use post consume scripts.
+  * An error in the consumer that cause invalid messages of missing files to show up in the log.
+
+* The documentation now contains information about bare metal installs and a section about
+  how to setup the development environment.
+
+paperless-ng 0.9.3
+##################
+
+* Setting ``PAPERLESS_AUTO_LOGIN_USERNAME`` replaces ``PAPERLESS_DISABLE_LOGIN``.
+  You have to specify your username.
+* Added a simple sanity checker that checks your documents for missing or orphaned files,
+  files with wrong checksums, inaccessible files, and documents with empty content.
+* It is no longer possible to encrypt your documents. For the time being, paperless will
+  continue to operate with already encrypted documents.
+* Fixes:
+
+  * Paperless now uses inotify again, since the watchdog was causing issues which I was not
+    aware of.
+  * Issue with the automatic classifier not working with only one tag.
+  * A couple issues with the search index being opened to eagerly.
+
+* Added lots of tests for various parts of the application.
+
 paperless-ng 0.9.2
 ##################
 
@@ -52,7 +241,7 @@ paperless-ng 0.9.0
 * **Added:** New frontend. Features:
 
   * Single page application: It's much more responsive than the django admin pages.
-  * Dashboard. Shows recently scanned documents, or todos, or other documents
+  * Dashboard. Shows recently scanned documents, or todo notes, or other documents
     at wish. Allows uploading of documents. Shows basic statistics.
   * Better document list with multiple display options.
   * Full text search with result highlighting, auto completion and scoring based
@@ -102,7 +291,7 @@ paperless-ng 0.9.0
 
 * **Modified [breaking]:** PostgreSQL:
 
-  * If ``PAPERLESS_DBHOST`` is specified in the settings, paperless uses postgresql instead of sqlite.
+  * If ``PAPERLESS_DBHOST`` is specified in the settings, paperless uses PostgreSQL instead of SQLite.
     Username, database and password all default to ``paperless`` if not specified.
 
 * **Modified [breaking]:** document_retagger management command rework. See
@@ -130,7 +319,7 @@ paperless-ng 0.9.0
     Certain language specifics such as umlauts may not get picked up properly.
   * ``PAPERLESS_DEBUG`` defaults to ``false``.
   * The presence of ``PAPERLESS_DBHOST`` now determines whether to use PostgreSQL or
-    sqlite.
+    SQLite.
   * ``PAPERLESS_OCR_THREADS`` is gone and replaced with ``PAPERLESS_TASK_WORKERS`` and
     ``PAPERLESS_THREADS_PER_WORKER``. Refer to the config example for details.
   * ``PAPERLESS_OPTIMIZE_THUMBNAILS`` allows you to disable or enable thumbnail
@@ -138,8 +327,11 @@ paperless-ng 0.9.0
 
 * Many more small changes here and there. The usual stuff.
 
+Paperless
+#########
+
 2.7.0
-#####
+=====
 
 * `syntonym`_ submitted a pull request to catch IMAP connection errors `#475`_.
 * `Stéphane Brunner`_ added ``psycopg2`` to the Pipfile `#489`_.  He also fixed
@@ -156,7 +348,7 @@ paperless-ng 0.9.0
 
 
 2.6.1
-#####
+=====
 
 * We now have a logo, complete with a favicon :-)
 * Removed some problematic tests.
@@ -168,7 +360,7 @@ paperless-ng 0.9.0
 
 
 2.6.0
-#####
+=====
 
 * Allow an infinite number of logs to be deleted.  Thanks to `Ulli`_ for noting
   the problem in `#433`_.
@@ -189,7 +381,7 @@ paperless-ng 0.9.0
 
 
 2.5.0
-#####
+=====
 
 * **New dependency**: Paperless now optimises thumbnail generation with
   `optipng`_, so you'll need to install that somewhere in your PATH or declare
@@ -233,7 +425,7 @@ paperless-ng 0.9.0
 
 
 2.4.0
-#####
+=====
 
 * A new set of actions are now available thanks to `jonaswinkler`_'s very first
   pull request!  You can now do nifty things like tag documents in bulk, or set
@@ -254,7 +446,7 @@ paperless-ng 0.9.0
 
 
 2.3.0
-#####
+=====
 
 * Support for consuming plain text & markdown documents was added by
   `Joshua Taillon`_!  This was a long-requested feature, and it's addition is
@@ -272,14 +464,14 @@ paperless-ng 0.9.0
 
 
 2.2.1
-#####
+=====
 
 * `Kyle Lucy`_ reported a bug quickly after the release of 2.2.0 where we broke
   the ``DISABLE_LOGIN`` feature: `#392`_.
 
 
 2.2.0
-#####
+=====
 
 * Thanks to `dadosch`_, `Wolfgang Mader`_, and `Tim Brooks`_ this is the first
   version of Paperless that supports Django 2.0!  As a result of their hard
@@ -296,7 +488,7 @@ paperless-ng 0.9.0
 
 
 2.1.0
-#####
+=====
 
 * `Enno Lohmeier`_ added three simple features that make Paperless a lot more
   user (and developer) friendly:
@@ -315,7 +507,7 @@ paperless-ng 0.9.0
 
 
 2.0.0
-#####
+=====
 
 This is a big release as we've changed a core-functionality of Paperless: we no
 longer encrypt files with GPG by default.
@@ -347,7 +539,7 @@ Special thanks to `erikarvstedt`_, `matthewmoto`_, and `mcronce`_ who did the
 bulk of the work on this big change.
 
 1.4.0
-#####
+=====
 
 * `Quentin Dawans`_ has refactored the document consumer to allow for some
   command-line options.  Notably, you can now direct it to consume from a
@@ -382,7 +574,7 @@ bulk of the work on this big change.
   to some excellent work from `erikarvstedt`_ on `#351`_
 
 1.3.0
-#####
+=====
 
 * You can now run Paperless without a login, though you'll still have to create
   at least one user.  This is thanks to a pull-request from `matthewmoto`_:
@@ -405,7 +597,7 @@ bulk of the work on this big change.
   problem and helping me find where to fix it.
 
 1.2.0
-#####
+=====
 
 * New Docker image, now based on Alpine, thanks to the efforts of `addadi`_
   and `Pit`_.  This new image is dramatically smaller than the Debian-based
@@ -424,7 +616,7 @@ bulk of the work on this big change.
   in the document text.
 
 1.1.0
-#####
+=====
 
 * Fix for `#283`_, a redirect bug which broke interactions with
   paperless-desktop.  Thanks to `chris-aeviator`_ for reporting it.
@@ -434,7 +626,7 @@ bulk of the work on this big change.
   `Dan Panzarella`_
 
 1.0.0
-#####
+=====
 
 * Upgrade to Django 1.11.  **You'll need to run
   ``pip install -r requirements.txt`` after the usual ``git pull`` to
@@ -453,14 +645,14 @@ bulk of the work on this big change.
   `Lukas Winkler`_'s issue `#278`_
 
 0.8.0
-#####
+=====
 
 * Paperless can now run in a subdirectory on a host (``/paperless``), rather
   than always running in the root (``/``) thanks to `maphy-psd`_'s work on
   `#255`_.
 
 0.7.0
-#####
+=====
 
 * **Potentially breaking change**: As per `#235`_, Paperless will no longer
   automatically delete documents attached to correspondents when those
@@ -472,7 +664,7 @@ bulk of the work on this big change.
   `Kusti Skytén`_ for posting the correct solution in the Github issue.
 
 0.6.0
-#####
+=====
 
 * Abandon the shared-secret trick we were using for the POST API in favour
   of BasicAuth or Django session.
@@ -486,7 +678,7 @@ bulk of the work on this big change.
   the help with this feature.
 
 0.5.0
-#####
+=====
 
 * Support for fuzzy matching in the auto-tagger & auto-correspondent systems
   thanks to `Jake Gysland`_'s patch `#220`_.
@@ -504,13 +696,13 @@ bulk of the work on this big change.
   * Amended the Django Admin configuration to have nice headers (`#230`_)
 
 0.4.1
-#####
+=====
 
 * Fix for `#206`_ wherein the pluggable parser didn't recognise files with
   all-caps suffixes like ``.PDF``
 
 0.4.0
-#####
+=====
 
 * Introducing reminders.  See `#199`_ for more information, but the short
   explanation is that you can now attach simple notes & times to documents
@@ -520,7 +712,7 @@ bulk of the work on this big change.
   like to make use of this feature in his project.
 
 0.3.6
-#####
+=====
 
 * Fix for `#200`_ (!!) where the API wasn't configured to allow updating the
   correspondent or the tags for a document.
@@ -534,7 +726,7 @@ bulk of the work on this big change.
   documentation is on its way.
 
 0.3.5
-#####
+=====
 
 * A serious facelift for the documents listing page wherein we drop the
   tabular layout in favour of a tiled interface.
@@ -545,7 +737,7 @@ bulk of the work on this big change.
   consumption.
 
 0.3.4
-#####
+=====
 
 * Removal of django-suit due to a licensing conflict I bumped into in 0.3.3.
   Note that you *can* use Django Suit with Paperless, but only in a
@@ -558,26 +750,26 @@ bulk of the work on this big change.
   API thanks to @thomasbrueggemann.  See `#179`_.
 
 0.3.3
-#####
+=====
 
 * Thumbnails in the UI and a Django-suit -based face-lift courtesy of @ekw!
 * Timezone, items per page, and default language are now all configurable,
   also thanks to @ekw.
 
 0.3.2
-#####
+=====
 
 * Fix for `#172`_: defaulting ALLOWED_HOSTS to ``["*"]`` and allowing the
   user to set her own value via ``PAPERLESS_ALLOWED_HOSTS`` should the need
   arise.
 
 0.3.1
-#####
+=====
 
 * Added a default value for ``CONVERT_BINARY``
 
 0.3.0
-#####
+=====
 
 * Updated to using django-filter 1.x
 * Added some system checks so new users aren't confused by misconfigurations.
@@ -590,7 +782,7 @@ bulk of the work on this big change.
   ``PAPERLESS_SHARED_SECRET`` respectively instead.
 
 0.2.0
-#####
+=====
 
 * `#150`_: The media root is now a variable you can set in
   ``paperless.conf``.
@@ -618,7 +810,7 @@ bulk of the work on this big change.
   to `Martin Honermeyer`_ and `Tim White`_ for working with me on this.
 
 0.1.1
-#####
+=====
 
 * Potentially **Breaking Change**: All references to "sender" in the code
   have been renamed to "correspondent" to better reflect the nature of the
@@ -642,7 +834,7 @@ bulk of the work on this big change.
   to be imported but made unavailable.
 
 0.1.0
-#####
+=====
 
 * Docker support!  Big thanks to `Wayne Werner`_, `Brian Conn`_, and
   `Tikitu de Jager`_ for this one, and especially to `Pit`_
@@ -661,14 +853,14 @@ bulk of the work on this big change.
 * Added tox with pep8 checking
 
 0.0.6
-#####
+=====
 
 * Added support for parallel OCR (significant work from `Pit`_)
 * Sped up the language detection (significant work from `Pit`_)
 * Added simple logging
 
 0.0.5
-#####
+=====
 
 * Added support for image files as documents (png, jpg, gif, tiff)
 * Added a crude means of HTTP POST for document imports
@@ -677,7 +869,7 @@ bulk of the work on this big change.
 * Documentation for the above as well as data migration
 
 0.0.4
-#####
+=====
 
 * Added automated tagging basted on keyword matching
 * Cleaned up the document listing page
@@ -685,22 +877,25 @@ bulk of the work on this big change.
 * Added ``pytz`` to the list of requirements
 
 0.0.3
-#####
+=====
 
 * Added basic tagging
 
 0.0.2
-#####
+=====
 
 * Added language detection
 * Added datestamps to ``document_exporter``.
 * Changed ``settings.TESSERACT_LANGUAGE`` to ``settings.OCR_LANGUAGE``.
 
 0.0.1
-#####
+=====
 
 * Initial release
 
+.. _rYR79435: https://github.com/rYR79435
+.. _Michael Shamoon: https://github.com/shamoon
+.. _jayme-github: http://github.com/jayme-github
 .. _Brian Conn: https://github.com/TheConnMan
 .. _Christopher Luu: https://github.com/nuudles
 .. _Florian Jung: https://github.com/the01

docs/conf.py

@@ -1,48 +1,21 @@
-# -*- coding: utf-8 -*-
-#
-# Paperless documentation build configuration file, created by
-# sphinx-quickstart on Mon Oct 26 18:36:52 2015.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
+import sphinx_rtd_theme
+
 
 __version__ = None
 exec(open("../src/paperless/version.py").read())
 
 
-# Believe it or not, this is the officially sanctioned way to add custom CSS.
-def setup(app):
-    app.add_stylesheet("custom.css")
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#sys.path.insert(0, os.path.abspath('.'))
-
-# -- General configuration ------------------------------------------------
-
-# If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
 extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.intersphinx',
     'sphinx.ext.todo',
     'sphinx.ext.imgmath',
     'sphinx.ext.viewcode',
+    'sphinx_rtd_theme',
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+# templates_path = ['_templates']
 
 # The suffix of source filenames.
 source_suffix = '.rst'
@@ -115,7 +88,7 @@ pygments_style = 'sphinx'
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'default'
+html_theme = 'sphinx_rtd_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -195,20 +168,6 @@ html_static_path = ['_static']
 # Output file base name for HTML help builder.
 htmlhelp_basename = 'paperless'
 
-
-#
-# Attempt to use the ReadTheDocs theme.  If it's not installed, fallback to
-# the default.
-#
-
-try:
-    import sphinx_rtd_theme
-    html_theme = "sphinx_rtd_theme"
-    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
-except ImportError as e:
-    print("error " + str(e))
-    pass
-
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {

docs/configuration.rst

@@ -35,22 +35,22 @@ PAPERLESS_DBHOST=<hostname>
 
 PAPERLESS_DBPORT=<port>
     Adjust port if necessary.
-    
+
     Default is 5432.
 
 PAPERLESS_DBNAME=<name>
     Database name in PostgreSQL.
-    
+
     Defaults to "paperless".
 
 PAPERLESS_DBUSER=<name>
     Database user in PostgreSQL.
-    
+
     Defaults to "paperless".
 
 PAPERLESS_DBPASS=<password>
     Database password for PostgreSQL.
-    
+
     Defaults to "paperless".
 
 
@@ -69,7 +69,7 @@ PAPERLESS_CONSUMPTION_DIR=<path>
     Defaults to "../consume", relative to the "src" directory.
 
 PAPERLESS_DATA_DIR=<path>
-    This is where paperless stores all its data (search index, sqlite database,
+    This is where paperless stores all its data (search index, SQLite database,
     classification model, etc).
 
     Defaults to "../data", relative to the "src" directory.
@@ -100,7 +100,7 @@ Hosting & Security
 ##################
 
 PAPERLESS_SECRET_KEY=<key>
-    Paperless uses this to make session tokens. If you exose paperless on the
+    Paperless uses this to make session tokens. If you expose paperless on the
     internet, you need to change this, since the default secret is well known.
 
     Use any sequence of characters. The more, the better. You don't need to
@@ -113,7 +113,7 @@ PAPERLESS_ALLOWED_HOSTS<comma-separated-list>
     really should set this value to the domain name you're using.  Failing to do
     so leaves you open to HTTP host header attacks:
     https://docs.djangoproject.com/en/3.1/topics/security/#host-header-validation
-    
+
     Just remember that this is a comma-separated list, so "example.com" is fine,
     as is "example.com,www.example.com", but NOT " example.com" or "example.com,"
 
@@ -132,16 +132,152 @@ PAPERLESS_FORCE_SCRIPT_NAME=<path>
     .. note::
 
         I don't know if this works in paperless-ng. Probably not.
-    
+
     Defaults to none, which hosts paperless at "/".
 
 PAPERLESS_STATIC_URL=<path>
     Override the STATIC_URL here.  Unless you're hosting Paperless off a
     subdomain like /paperless/, you probably don't need to change this.
-    
+
     Defaults to "/static/".
 
+PAPERLESS_AUTO_LOGIN_USERNAME=<username>
+    Specify a username here so that paperless will automatically perform login
+    with the selected user.
 
+    .. danger::
+
+        Do not use this when exposing paperless on the internet. There are no
+        checks in place that would prevent you from doing this.
+
+    Defaults to none, which disables this feature.
+
+
+PAPERLESS_COOKIE_PREFIX=<str>
+    Specify a prefix that is added to the cookies used by paperless to identify
+    the currently logged in user. This is useful for when you're running two
+    instances of paperless on the same host.
+
+    After changing this, you will have to login again.
+
+    Defaults to ``""``, which does not alter the cookie names.
+
+.. _configuration-ocr:
+
+OCR settings
+############
+
+Paperless uses `OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/>`_ for
+performing OCR on documents and images. Paperless uses sensible defaults for
+most settings, but all of them can be configured to your needs.
+
+
+PAPERLESS_OCR_LANGUAGE=<lang>
+    Customize the language that paperless will attempt to use when
+    parsing documents.
+
+    It should be a 3-letter language code consistent with ISO
+    639: https://www.loc.gov/standards/iso639-2/php/code_list.php
+
+    Set this to the language most of your documents are written in.
+
+    This can be a combination of multiple languages such as ``deu+eng``,
+    in which case tesseract will use whatever language matches best.
+    Keep in mind that tesseract uses much more cpu time with multiple
+    languages enabled.
+
+    Defaults to "eng".
+
+PAPERLESS_OCR_MODE=<mode>
+    Tell paperless when and how to perform ocr on your documents. Four modes
+    are available:
+
+    *   ``skip``: Paperless skips all pages and will perform ocr only on pages
+        where no text is present. This is the safest option.
+    *   ``skip_noarchive``: In addition to skip, paperless won't create an
+        archived version of your documents when it finds any text in them.
+        This is useful if you don't want to have two almost-identical versions
+        of your digital documents in the media folder. This is the fastest option.
+    *   ``redo``: Paperless will OCR all pages of your documents and attempt to
+        replace any existing text layers with new text. This will be useful for
+        documents from scanners that already performed OCR with insufficient
+        results. It will also perform OCR on purely digital documents.
+
+        This option may fail on some documents that have features that cannot
+        be removed, such as forms. In this case, the text from the document is
+        used instead.
+    *   ``force``: Paperless rasterizes your documents, converting any text
+        into images and puts the OCRed text on top. This works for all documents,
+        however, the resulting document may be significantly larger and text
+        won't appear as sharp when zoomed in.
+    
+    The default is ``skip``, which only performs OCR when necessary and always
+    creates archived documents.
+
+PAPERLESS_OCR_OUTPUT_TYPE=<type>
+    Specify the the type of PDF documents that paperless should produce.
+    
+    *   ``pdf``: Modify the PDF document as little as possible.
+    *   ``pdfa``: Convert PDF documents into PDF/A-2b documents, which is a
+        subset of the entire PDF specification and meant for storing
+        documents long term.
+    *   ``pdfa-1``, ``pdfa-2``, ``pdfa-3`` to specify the exact version of
+        PDF/A you wish to use.
+    
+    If not specified, ``pdfa`` is used. Remember that paperless also keeps
+    the original input file as well as the archived version.
+
+
+PAPERLESS_OCR_PAGES=<num>
+    Tells paperless to use only the specified amount of pages for OCR. Documents
+    with less than the specified amount of pages get OCR'ed completely.
+
+    Specifying 1 here will only use the first page.
+
+    When combined with ``PAPERLESS_OCR_MODE=redo`` or ``PAPERLESS_OCR_MODE=force``,
+    paperless will not modify any text it finds on excluded pages and copy it
+    verbatim.
+
+    Defaults to 0, which disables this feature and always uses all pages.
+
+
+PAPERLESS_OCR_IMAGE_DPI=<num>
+    Paperless will OCR any images you put into the system and convert them
+    into PDF documents. This is useful if your scanner produces images.
+    In order to do so, paperless needs to know the DPI of the image.
+    Most images from scanners will have this information embedded and
+    paperless will detect and use that information. In case this fails, it
+    uses this value as a fallback.
+
+    Set this to the DPI your scanner produces images at.
+
+    Default is none, which causes paperless to fail if no DPI information is
+    present in an image.
+
+
+PAPERLESS_OCR_USER_ARG=<json>
+    OCRmyPDF offers many more options. Use this parameter to specify any
+    additional arguments you wish to pass to OCRmyPDF. Since Paperless uses
+    the API of OCRmyPDF, you have to specify these in a format that can be
+    passed to the API. See `the API reference of OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/api.html#reference>`_
+    for valid parameters. All command line options are supported, but they
+    use underscores instead of dashed.
+
+    .. caution::
+
+        Paperless has been tested to work with the OCR options provided
+        above. There are many options that are incompatible with each other,
+        so specifying invalid options may prevent paperless from consuming
+        any documents.
+
+    Specify arguments as a JSON dictionary. Keep note of lower case booleans
+    and double quoted parameter names and strings. Examples:
+
+    .. code:: json
+
+        {"deskew": true, "optimize": 3, "unpaper_args": "--pre-rotate 90"}    
+    
+    
 Software tweaks
 ###############
 
@@ -150,17 +286,18 @@ PAPERLESS_TASK_WORKERS=<num>
     maintain the automatic matching algorithm, check emails, consume documents,
     etc. This variable specifies how many things it will do in parallel.
 
+
 PAPERLESS_THREADS_PER_WORKER=<num>
     Furthermore, paperless uses multiple threads when consuming documents to
     speed up OCR. This variable specifies how many pages paperless will process
     in parallel on a single document.
 
     .. caution::
-        
+
         Ensure that the product
-        
+
             PAPERLESS_TASK_WORKERS * PAPERLESS_THREADS_PER_WORKER
-        
+
         does not exceed your CPU core count or else paperless will be extremely slow.
         If you want paperless to process many documents in parallel, choose a high
         worker count. If you want paperless to process very large documents faster,
@@ -174,7 +311,6 @@ PAPERLESS_THREADS_PER_WORKER=<num>
     PAPERLESS_THREADS_PER_WORKER automatically.
 
 
-
 PAPERLESS_TIME_ZONE=<timezone>
     Set the time zone here.
     See https://docs.djangoproject.com/en/3.1/ref/settings/#std:setting-TIME_ZONE
@@ -183,44 +319,14 @@ PAPERLESS_TIME_ZONE=<timezone>
     Defaults to UTC.
 
 
-
-PAPERLESS_OCR_PAGES=<num>
-    Tells paperless to use only the specified amount of pages for OCR. Documents
-    with less than the specified amount of pages get OCR'ed completely.
-
-    Specifying 1 here will only use the first page.
-
-    Defaults to 0, which disables this feature and always uses all pages.
-
-
-
-PAPERLESS_OCR_LANGUAGE=<lang>
-    Customize the default language that tesseract will attempt to use when
-    parsing documents. The default language is used whenever
-    
-    * No language could be detected on a document
-    * No tesseract data files are available for the detected language
-    
-    It should be a 3-letter language code consistent with ISO
-    639: https://www.loc.gov/standards/iso639-2/php/code_list.php
-
-    Set this to the language most of your documents are written in.
-
-    Defaults to "eng".
-
-PAPERLESS_OCR_ALWAYS=<bool>
-    By default Paperless does not OCR a document if the text can be retrieved from
-    the document directly. Set to true to always OCR documents.
-
-    Defaults to false.
-
 PAPERLESS_CONSUMER_POLLING=<num>
     If paperless won't find documents added to your consume folder, it might
     not be able to automatically detect filesystem changes. In that case,
     specify a polling interval in seconds here, which will then cause paperless
     to periodically check your consumption directory for changes.
 
-    Defaults to 0, which disables polling and uses filesystem notifiactions.
+    Defaults to 0, which disables polling and uses filesystem notifications.
+
 
 PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>
     When the consumer detects a duplicate document, it will not touch the
@@ -228,13 +334,32 @@ PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>
 
     Defaults to false.
 
+
+PAPERLESS_CONSUMER_RECURSIVE=<bool>
+    Enable recursive watching of the consumption directory. Paperless will
+    then pickup files from files in subdirectories within your consumption
+    directory as well.
+
+    Defaults to false.
+
+
+PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=<bool>
+    Set the names of subdirectories as tags for consumed files.
+    E.g. <CONSUMPTION_DIR>/foo/bar/file.pdf will add the tags "foo" and "bar" to
+    the consumed file. Paperless will create any tags that don't exist yet.
+
+    PAPERLESS_CONSUMER_RECURSIVE must be enabled for this to work.
+
+    Defaults to false.
+
+
 PAPERLESS_CONVERT_MEMORY_LIMIT=<num>
     On smaller systems, or even in the case of Very Large Documents, the consumer
     may explode, complaining about how it's "unable to extend pixel cache".  In
     such cases, try setting this to a reasonably low value, like 32.  The
     default is to use whatever is necessary to do everything without writing to
     disk, and units are in megabytes.
-    
+
     For more information on how to use this value, you should search
     the web for "MAGICK_MEMORY_LIMIT".
 
@@ -245,26 +370,14 @@ PAPERLESS_CONVERT_TMPDIR=<path>
     /tmp as tmpfs, you should set this to a path that's on a physical disk, like
     /home/your_user/tmp or something.  ImageMagick will use this as scratch space
     when crunching through very large documents.
-    
+
     For more information on how to use this value, you should search
     the web for "MAGICK_TMPDIR".
 
     Default is none, which disables the temporary directory.
 
-PAPERLESS_CONVERT_DENSITY=<num>
-    This setting has a high impact on the physical size of tmp page files,
-    the speed of document conversion, and can affect the accuracy of OCR
-    results. Individual results can vary and this setting should be tested
-    thoroughly against the documents you are importing to see if it has any
-    impacts either negative or positive.
-    Testing on limited document sets has shown a setting of 200 can cut the
-    size of tmp files by 1/3, and speed up conversion by up to 4x
-    with little impact to OCR accuracy.
-
-    Default is 300.
-
 PAPERLESS_OPTIMIZE_THUMBNAILS=<bool>
-    Use optipng to optimize thumbnails. This usually reduces the sice of
+    Use optipng to optimize thumbnails. This usually reduces the size of
     thumbnails by about 20%, but uses considerable compute time during
     consumption.
 
@@ -282,7 +395,7 @@ PAPERLESS_FILENAME_DATE_ORDER=<format>
     Use this setting to enable checking the document filename for date
     information. The date order can be set to any option as specified in
     https://dateparser.readthedocs.io/en/latest/settings.html#date-order.
-    The filename will be checked first, and if nothing is found, the document 
+    The filename will be checked first, and if nothing is found, the document
     text will be checked as normal.
 
     Defaults to none, which disables this feature.
@@ -309,8 +422,5 @@ PAPERLESS_CONVERT_BINARY=<path>
 PAPERLESS_GS_BINARY=<path>
     Defaults to "/usr/bin/gs".
 
-PAPERLESS_UNPAPER_BINARY=<path>
-    Defaults to "/usr/bin/unpaper".
-
 PAPERLESS_OPTIPNG_BINARY=<path>
     Defaults to "/usr/bin/optipng".

docs/contributing.rst

@@ -85,7 +85,7 @@ quoted, or triple-quoted string will do:
     problematic_string = 'This is a "string" with "quotes" in it'
 
 In HTML templates, please use double-quotes for tag attributes, and single
-quotes for arguments passed to Django tempalte tags:
+quotes for arguments passed to Django template tags:
 
 .. code:: html
 

docs/extending.rst

@@ -1,116 +1,197 @@
 .. _extending:
 
+Paperless development
+#####################
+
+This section describes the steps you need to take to start development on paperless-ng.
+
+1.  Check out the source from github. The repository is organized in the following way:
+
+    *   ``master`` always represents the latest release and will only see changes
+        when a new release is made.
+    *   ``dev`` contains the code that will be in the next release.
+    *   ``feature-X`` contain bigger changes that will be in some release, but not
+        necessarily the next one.
+    
+    Apart from that, the folder structure is as follows:
+
+    *   ``docs/`` - Documentation.
+    *   ``src-ui/`` - Code of the front end.
+    *   ``src/`` - Code of the back end.
+    *   ``scripts/`` - Various scripts that help with different parts of development.
+    *   ``docker/`` - Files required to build the docker image.
+
+2.  Install some dependencies.
+
+    *   Python 3.6.
+    *   All dependencies listed in the :ref:`Bare metal route <setup-bare_metal>`
+    *   redis. You can either install redis or use the included scritps/start-redis.sh
+        to use docker to fire up a redis instance.
+
+Back end development
+====================
+
+The backend is a django application. I use PyCharm for development, but you can use whatever
+you want.
+
+Install the python dependencies by performing ``pipenv install --dev`` in the src/ directory.
+This will also create a virtual environment, which you can enter with ``pipenv shell`` or
+execute one-shot commands in with ``pipenv run``.
+
+In ``src/paperless.conf``, enable debug mode.
+
+Configure the IDE to use the src/ folder as the base source folder. Configure the following
+launch configurations in your IDE:
+
+*   python3 manage.py runserver
+*   python3 manage.py qcluster
+*   python3 manage.py consumer
+
+Depending on which part of paperless you're developing for, you need to have some or all of
+them running.
+
+Testing and code style:
+
+*   Run ``pytest`` in the src/ directory to execute all tests. This also generates a HTML coverage
+    report. When runnings test, paperless.conf is loaded as well. However: the tests rely on the default
+    configuration. This is not ideal. But for now, make sure no settings except for DEBUG are overridden when testing.
+*   Run ``pycodestyle`` to test your code for issues with the configured code style settings.
+
+    .. note::
+
+        The line length rule E501 is generally useful for getting multiple source files
+        next to each other on the screen. However, in some cases, its just not possible
+        to make some lines fit, especially complicated IF cases. Append ``  # NOQA: E501``
+        to disable this check for certain lines.
+
+Front end development
+=====================
+
+The front end is build using angular. I use the ``Code - OSS`` IDE for development.
+
+In order to get started, you need ``npm``. Install the Angular CLI interface with
+
+.. code:: shell-session
+
+    $ npm install -g @angular/cli
+
+and make sure that it's on your path. Next, in the src-ui/ directory, install the
+required dependencies of the project.
+
+.. code:: shell-session
+
+    $ npm install
+
+You can launch a development server by running
+
+.. code:: shell-session
+
+    $ ng serve
+
+This will automatically update whenever you save. However, in-place compilation might fail
+on syntax errors, in which case you need to restart it.
+
+By default, the development server is available on ``http://localhost:4200/`` and is configured
+to access the API at ``http://localhost:8000/api/``, which is the default of the backend.
+If you enabled DEBUG on the back end, several security overrides for allowed hosts, CORS and
+X-Frame-Options are in place so that the front end behaves exactly as in production. This also
+relies on you being logged into the back end. Without a valid session, The front end will simply
+not work.
+
+In order to build the front end and serve it as part of django, execute
+
+.. code:: shell-session
+
+    $ ng build --prod --output-path ../src/documents/static/frontend/
+
+This will build the front end and put it in a location from which the Django server will serve
+it as static content. This way, you can verify that authentication is working.
+
+Making a release
+================
+
+Execute the ``make-release.sh <ver>`` script.
+
+This will test and assemble everything and also build and tag a docker image.
+
+
 Extending Paperless
 ===================
 
-.. warning::
+Paperless does not have any fancy plugin systems and will probably never have. However,
+some parts of the application have been designed to allow easy integration of additional
+features without any modification to the base code.
 
-    This section is not updated to paperless-ng yet.
+Making custom parsers
+---------------------
 
-For the most part, Paperless is monolithic, so extending it is often best
-managed by way of modifying the code directly and issuing a pull request on
-`GitHub`_.  However, over time the project has been evolving to be a little
-more "pluggable" so that users can write their own stuff that talks to it.
+Paperless uses parsers to add documents to paperless. A parser is responsible for:
 
-.. _GitHub: https://github.com/the-paperless-project/paperless
+*   Retrieve the content from the original
+*   Create a thumbnail
+*   Optional: Retrieve a created date from the original
+*   Optional: Create an archived document from the original
 
+Custom parsers can be added to paperless to support more file types. In order to do that,
+you need to write the parser itself and announce its existence to paperless.
 
-.. _extending-parsers:
-
-Parsers
--------
-
-You can leverage Paperless' consumption model to have it consume files *other*
-than ones handled by default like ``.pdf``, ``.jpg``, and ``.tiff``.  To do so,
-you simply follow Django's convention of creating a new app, with a few key
-requirements.
-
-
-.. _extending-parsers-parserspy:
-
-parsers.py
-..........
-
-In this file, you create a class that extends
-``documents.parsers.DocumentParser`` and go about implementing the three
-required methods:
-
-* ``get_thumbnail()``: Returns the path to a file we can use as a thumbnail for
-  this document.
-* ``get_text()``: Returns the text from the document and only the text.
-* ``get_date()``: If possible, this returns the date of the document, otherwise
-  it should return ``None``.
-
-
-.. _extending-parsers-signalspy:
-
-signals.py
-..........
-
-At consumption time, Paperless emits a ``document_consumer_declaration``
-signal which your module has to react to in order to let the consumer know
-whether or not it's capable of handling a particular file.  Think of it like
-this:
-
-1. Consumer finds a file in the consumption directory.
-2. It asks all the available parsers: *"Hey, can you handle this file?"*
-3. Each parser responds with either ``None`` meaning they can't handle the
-   file, or a dictionary in the following format:
+The parser itself must extend ``documents.parsers.DocumentParser`` and must implement the
+methods ``parse`` and ``get_thumbnail``. You can provide your own implementation to
+``get_date`` if you don't want to rely on paperless' default date guessing mechanisms.
 
 .. code:: python
 
-    {
-        "parser": <the class name>,
-        "weight": <an integer>
-    }
+    class MyCustomParser(DocumentParser):
 
-The consumer compares the ``weight`` values from all respondents and uses the
-class with the highest value to consume the document.  The default parser,
-``RasterisedDocumentParser`` has a weight of ``0``.
+        def parse(self, document_path, mime_type):
+            # This method does not return anything. Rather, you should assign
+            # whatever you got from the document to the following fields:
 
+            # The content of the document.
+            self.text = "content"
+            
+            # Optional: path to a PDF document that you created from the original.
+            self.archive_path = os.path.join(self.tempdir, "archived.pdf")
 
-.. _extending-parsers-appspy:
+            # Optional: "created" date of the document.
+            self.date = get_created_from_metadata(document_path)
 
-apps.py
-.......
+        def get_thumbnail(self, document_path, mime_type):
+            # This should return the path to a thumbnail you created for this
+            # document.
+            return os.path.join(self.tempdir, "thumb.png")
 
-This is a standard Django file, but you'll need to add some code to it to
-connect your parser to the ``document_consumer_declaration`` signal.
+If you encounter any issues during parsing, raise a ``documents.parsers.ParseError``.
 
+The ``self.tempdir`` directory is a temporary directory that is guaranteed to be empty
+and removed after consumption finished. You can use that directory to store any
+intermediate files and also use it to store the thumbnail / archived document.
 
-.. _extending-parsers-finally:
-
-Finally
-.......
-
-The last step is to update ``settings.py`` to include your new module.
-Eventually, this will be dynamic, but at the moment, you have to edit the
-``INSTALLED_APPS`` section manually.  Simply add the path to your AppConfig to
-the list like this:
+After that, you need to announce your parser to paperless. You need to connect a
+handler to the ``document_consumer_declaration`` signal. Have a look in the file
+``src/paperless_tesseract/apps.py`` on how that's done. The handler is a method
+that returns information about your parser:
 
 .. code:: python
 
-    INSTALLED_APPS = [
-        ...
-        "my_module.apps.MyModuleConfig",
-        ...
-    ]
+    def myparser_consumer_declaration(sender, **kwargs):
+        return {
+            "parser": MyCustomParser,
+            "weight": 0,
+            "mime_types": {
+                "application/pdf": ".pdf",
+                "image/jpeg": ".jpg",
+            }
+        }
 
-Order doesn't matter, but generally it's a good idea to place your module lower
-in the list so that you don't end up accidentally overriding project defaults
-somewhere.
+*   ``parser`` is a reference to a class that extends ``DocumentParser``.
 
+*   ``weight`` is used whenever two or more parsers are able to parse a file: The parser with
+    the higher weight wins. This can be used to override the parsers provided by
+    paperless.
 
-.. _extending-parsers-example:
-
-An Example
-..........
-
-The core Paperless functionality is based on this design, so if you want to see
-what a parser module should look like, have a look at `parsers.py`_,
-`signals.py`_, and `apps.py`_ in the `paperless_tesseract`_ module.
-
-.. _parsers.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/parsers.py
-.. _signals.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/signals.py
-.. _apps.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/apps.py
-.. _paperless_tesseract: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/
+*   ``mime_types`` is a dictionary. The keys are the mime types your parser supports and the value
+    is the default file extension that paperless should use when storing files and serving them for
+    download. We could guess that from the file extensions, but some mime types have many extensions
+    associated with them and the python methods responsible for guessing the extension do not always
+    return the same value.

docs/faq.rst

@@ -3,6 +3,18 @@
 Frequently asked questions
 **************************
 
+**Q:** *What's the general plan for Paperless-ng?*
+
+**A:** Paperless-ng is already almost feature-complete. This project will remain
+as simple as it is right now. It will see improvements to features that are already there.
+If you need advanced features such as document versions,
+workflows or multi-user with customizable access to individual files, this is
+not the tool for you.
+
+Features that *are* planned are some more quality of life extensions for the searching
+(i.e., search for similar documents, group results by correspondents with "more from this"
+links, etc), bulk editing and hierarchical tags.
+
 **Q:** *I'm using docker. Where are my documents?*
 
 **A:** Your documents are stored inside the docker volume ``paperless_media``.
@@ -17,15 +29,27 @@ is
 
 .. caution::
 
-    Dont mess with this folder. Don't change permissions and don't move
+    Do not mess with this folder. Don't change permissions and don't move
     files around manually. This folder is meant to be entirely managed by docker
     and paperless.
 
+**Q:** *Let's say you don't support this project anymore in a year. Can I easily move to other systems?*
+
+**A:** Your documents are stored as plain files inside the media folder. You can always drag those files
+out of that folder to use them elsewhere. Here are a couple notes about that.
+
+*   Paperless never modifies your original documents. It keeps checksums of all documents and uses a
+    scheduled sanity checker to check that they remain the same.
+*   By default, paperless uses the internal ID of each document as its filename. This might not be very
+    convenient for export. However, you can adjust the way files are stored in paperless by
+    :ref:`configuring the filename format <advanced-file_name_handling>`.
+*   :ref:`The exporter <utilities-exporter>` is another easy way to get your files out of paperless with reasonable file names.
+
 **Q:** *What file types does paperless-ng support?*
 
 **A:** Currently, the following files are supported:
 
-*   PDF documents, PNG images and JPEG images are processed with OCR.
+*   PDF documents, PNG images, JPEG images, TIFF images and GIF images are processed with OCR and converted into PDF documents.
 *   Plain text documents are supported as well and are added verbatim
     to paperless.
 
@@ -36,9 +60,9 @@ file extensions do not matter.
 
 **A:** The short answer is yes. I've tested it on a Raspberry Pi 3 B.
 The long answer is that certain parts of
-Paperless will run very slow, such as the tesseract OCR. On Rasperry Pi,
+Paperless will run very slow, such as the tesseract OCR. On Raspberry Pi,
 try to OCR documents before feeding them into paperless so that paperless can
-reuse the text. The web interface should be alot snappier, since it runs
+reuse the text. The web interface should be a lot snappier, since it runs
 in your browser and paperless has to do much less work to serve the data.
 
 .. note::
@@ -49,7 +73,34 @@ in your browser and paperless has to do much less work to serve the data.
 
 **Q:** *How do I install paperless-ng on Raspberry Pi?*
 
-**A:** There is not docker image for ARM available. If you know how to build
+**A:** There is no docker image for ARM available. If you know how to build
 that automatically, I'm all ears. For now, you have to grab the latest release
 archive from the project page and build the image yourself. The release comes
 with the front end already compiled, so you don't have to do this on the Pi.
+
+**Q:** *How do I run this on unRaid?*
+
+**A:** Head over to `<https://github.com/selfhosters/unRAID-CA-templates>`_,
+`Uli Fahrer <https://github.com/Tooa>`_ created a container template for that.
+I don't exactly know how to use that though, since I don't use unRaid.
+
+**Q:** *How do I run this on my toaster?*
+
+**A:** I honestly don't know! As for all other devices that might be able
+to run paperless, you're a bit on your own. If you can't run the docker image,
+the documentation has instructions for bare metal installs. I'm running
+paperless on an i3 processor from 2015 or so. This is also what I use to test
+new releases with. Apart from that, I also have a Raspberry Pi, which I
+occasionally build the image on and see if it works.
+
+**Q:** *How do I proxy this with NGINX?*
+
+.. code::
+
+    location / {
+        proxy_pass http://localhost:8000/
+    }
+
+And that's about it. Paperless serves everything, including static files by itself
+when running the docker image. If you want to do anything fancy, you have to
+install paperless bare metal.

docs/index.rst

@@ -42,6 +42,9 @@ resources in the documentation:
     learn about how paperless automates all tagging using machine learning.
 *   Paperless now comes with a :ref:`proper email consumer <usage-email>`
     that's fully tested and production ready.
+*   Paperless creates searchable PDF/A documents from whatever you you put into
+    the consumption directory. This means that you can select text in
+    image-only documents coming from your scanner.
 *   See :ref:`this note <utilities-encyption>` about GnuPG encryption in
     paperless-ng.
 *   Paperless is now integrated with a

docs/scanners.rst

@@ -8,7 +8,7 @@ Scanner recommendations
 As Paperless operates by watching a folder for new files, doesn't care what
 scanner you use, but sometimes finding a scanner that will write to an FTP,
 NFS, or SMB server can be difficult.  This page is here to help you find one
-that works right for you based on recommentations from other Paperless users.
+that works right for you based on recommendations from other Paperless users.
 
 +---------+----------------+-----+-----+-----+----------------+
 | Brand   | Model          | Supports        | Recommended By |

docs/screenshots.rst

@@ -9,41 +9,37 @@ research papers though, its a horrible tool for that job.
 
 The dashboard shows customizable views on your document and allows document uploads:
 
-.. image:: _static/paperless-0-dashboard.png
+.. image:: _static/screenshots/dashboard.png
 
 The document list provides three different styles to scroll through your documents:
 
-.. image:: _static/paperless-1-list-table.png
-.. image:: _static/paperless-2-list-smallcards.png
-.. image:: _static/paperless-3-list-largecards.png
+.. image:: _static/screenshots/documents-table.png
+.. image:: _static/screenshots/documents-smallcards.png
+.. image:: _static/screenshots/documents-largecards.png
 
 Extensive filtering mechanisms:
 
-.. image:: _static/paperless-4-filter.png
+.. image:: _static/screenshots/documents-filter.png
 
-Side-by-side editing of documents. Optmized for 1080p.
+Side-by-side editing of documents. Optimized for 1080p.
 
-.. image:: _static/paperless-5-editing.png
+.. image:: _static/screenshots/editing.png
 
 Tag editing. This looks about the same for correspondents and document types.
 
-.. image:: _static/paperless-6-tags.png
+.. image:: _static/screenshots/new-tag.png
 
 Searching provides auto complete and highlights the results.
 
-.. image:: _static/paperless-7-autocomplete.png
-.. image:: _static/paperless-8-search-results.png
-
-The old admin is still there and accessible!
-
-.. image:: _static/paperless-9-admin.png
+.. image:: _static/screenshots/search-preview.png
+.. image:: _static/screenshots/search-results.png
 
 Fancy mail filters!
 
-.. image:: _static/paperless-11-mail-filters.png
+.. image:: _static/screenshots/mail-rules-edited.png
 
 Mobile support in the future? This kinda works, however some layouts are still
 too wide.
 
-.. image:: _static/paperless-10-mobile.png
+.. image:: _static/screenshots/mobile.png
 

docs/setup.rst

@@ -85,7 +85,7 @@ Paperless consists of the following components:
         needs to do from time to time in order to operate properly.
 
     This allows paperless to process multiple documents from your consumption folder in parallel! On
-    a modern multicore system, consumption with full ocr is blazing fast.
+    a modern multi core system, consumption with full ocr is blazing fast.
 
     The task processor comes with a built-in admin interface that you can use to see whenever any of the
     tasks fail and inspect the errors (i.e., wrong email credentials, errors during consuming a specific
@@ -102,8 +102,7 @@ Paperless consists of the following components:
     for getting the tasks from the webserver and consumer to the task scheduler. These run in different
     processes (maybe even on different machines!), and therefore, this is necessary.
 
-*   A database server. Paperless supports PostgreSQL and sqlite for storing its data. However, with the
-    added concurrency, it is strongly advised to use PostgreSQL, as sqlite has its limits in that regard.
+*   Optional: A database server. Paperless supports both PostgreSQL and SQLite for storing its data.
 
 
 Installation
@@ -146,10 +145,10 @@ Docker Route
 
     .. hint::
 
-        For new installations, it is recommended to use postgresql as the database
-        backend. This is due to the increased amount of concurrency in paperless-ng.
+        For new installations, it is recommended to use PostgreSQL as the database
+        backend.
 
-2.  Modify ``docker-compose.yml`` to your preferences. You should change the path
+2.  Modify ``docker-compose.yml`` to your preferences. You may want to change the path
     to the consumption directory in this file. Find the line that specifies where
     to mount the consumption directory:
 
@@ -205,13 +204,161 @@ Docker Route
    simplifies deployment immensely. If you know your way around Docker, feel
    free to tinker around without using compose!
 
+.. _`setup-bare_metal`:
 
 Bare Metal Route
 ================
 
-.. warning::
+Paperless runs on linux only. The following procedure has been tested on a minimal
+installation of Debian/Buster, which is the current stable release at the time of
+writing. Windows is not and will never be supported.
 
-    TBD. User docker for now.
+1.  Install dependencies. Paperless requires the following packages.
+
+    *   ``python3`` 3.6, 3.7, 3.8 (3.9 is untested).
+    *   ``python3-pip``, optionally ``pipenv`` for package installation
+    *   ``python3-dev``
+
+    *   ``imagemagick`` >= 6 for PDF conversion
+    *   ``optipng`` for optimising thumbnails
+    *   ``gnupg`` for handling encrypted documents
+    *   ``libpoppler-cpp-dev`` for PDF to text conversion
+    *   ``libmagic-dev`` for mime type detection
+    *   ``libpq-dev`` for PostgreSQL
+
+    These dependencies are required for OCRmyPDF, which is used for text recognition.
+
+    *   ``unpaper``
+    *   ``ghostscript``
+    *   ``icc-profiles-free``
+    *   ``qpdf``
+    *   ``liblept5``
+    *   ``libxml2``
+    *   ``pngquant``
+    *   ``zlib1g``
+    *   ``tesseract-ocr`` >= 4.0.0 for OCR
+    *   ``tesseract-ocr`` language packs (``tesseract-ocr-eng``, ``tesseract-ocr-deu``, etc)
+
+    You will also need ``build-essential``, ``python3-setuptools`` and ``python3-wheel``
+    for installing some of the python dependencies. You can remove that
+    again after installation.
+
+2.  Install ``redis`` >= 5.0 and configure it to start automatically.
+
+3.  Optional. Install ``postgresql`` and configure a database, user and password for paperless. If you do not wish
+    to use PostgreSQL, SQLite is avialable as well.
+
+4.  Get the release archive. If you pull the git repo as it is, you also have to compile the front end by yourself.
+    Extract the frontend to a place from where you wish to execute it, such as ``/opt/paperless``.
+
+5.  Configure paperless. See :ref:`configuration` for details. Edit the included ``paperless.conf`` and adjust the
+    settings to your needs. Required settings for getting paperless running are:
+
+    *   ``PAPERLESS_REDIS`` should point to your redis server, such as redis://localhost:6379.
+    *   ``PAPERLESS_DBHOST`` should be the hostname on which your PostgreSQL server is running. Do not configure this
+        to use SQLite instead. Also configure port, database name, user and password as necessary.
+    *   ``PAPERLESS_CONSUMPTION_DIR`` should point to a folder which paperless should watch for documents. You might
+        want to have this somewhere else. Likewise, ``PAPERLESS_DATA_DIR`` and ``PAPERLESS_MEDIA_ROOT`` define where
+        paperless stores its data. If you like, you can point both to the same directory.
+    *   ``PAPERLESS_SECRET_KEY`` should be a random sequence of characters. It's used for authentication. Failure
+        to do so allows third parties to forge authentication credentials.
+    
+    Many more adjustments can be made to paperless, especially the OCR part. The following options are recommended
+    for everyone:
+
+    *   Set ``PAPERLESS_OCR_LANGUAGE`` to the language most of your documents are written in.
+    *   Set ``PAPERLESS_TIME_ZONE`` to your local time zone.
+
+6.  Setup permissions. Create a system users under which you wish to run paperless. Ensure that these directories exist
+    and that the user has write permissions to the following directories
+    
+    *   ``/opt/paperless/media``
+    *   ``/opt/paperless/data``
+    *   ``/opt/paperless/consume``
+
+    Adjust as necessary if you configured different folders.
+
+7.  Install python requirements. Paperless comes with both Pipfiles for ``pipenv`` as well as with a ``requirements.txt``.
+    Both will install exactly the same requirements. It is up to you if you wish to use a virtual environment or not.
+
+8.  Go to ``/opt/paperless/src``, and execute the following commands:
+
+    .. code:: bash
+
+        # This collects static files from paperless and django.
+        python3 manage.py collectstatic --clear --no-input
+        
+        # This creates the database schema.
+        python3 manage.py migrate
+
+        # This creates your first paperless user
+        python3 manage.py createsuperuser
+
+9.  Optional: Test that paperless is working by executing
+
+      .. code:: bash
+
+        # This collects static files from paperless and django.
+        python3 manage.py runserver
+    
+    and pointing your browser to http://localhost:8000/.
+
+    .. warning::
+
+        This is a development server which should not be used in
+        production.
+
+    .. hint::
+
+        This will not start the consumer. Paperless does this in a
+        separate process.
+
+10. Setup systemd services to run paperless automatically. You may
+    use the service definition files included in the ``scripts`` folder
+    as a starting point.
+
+    Paperless needs the ``webserver`` script to run the webserver, the
+    ``consumer`` script to watch the input folder, and the ``scheduler``
+    script to run tasks such as email checking and document consumption.
+
+    These services rely on redis and optionally the database server, but
+    don't need to be started in any particular order. The example files
+    depend on redis being started. If you use a database server, you should
+    add additinal dependencies.
+
+    .. hint::
+
+        You may optionally set up your preferred web server to serve
+        paperless as a wsgi application directly instead of running the
+        ``webserver`` service. The module containing the wsgi application
+        is named ``paperless.wsgi``.
+
+    .. caution::
+
+        The included scripts run a ``gunicorn`` standalone server,
+        which is fine for running paperless. It does support SSL,
+        however, the documentation of GUnicorn states that you should
+        use a proxy server in front of gunicorn instead.
+
+11. Optional: Install a samba server and make the consumption folder
+    available as a network share.
+
+12. Configure ImageMagick to allow processing of PDF documents. Most distributions have
+    this disabled by default, since PDF documents can contain malware. If
+    you don't do this, paperless will fall back to ghostscript for certain steps
+    such as thumbnail generation.
+
+    Edit ``/etc/ImageMagick-6/policy.xml`` and adjust
+
+    .. code::
+
+        <policy domain="coder" rights="none" pattern="PDF" />
+    
+    to
+
+    .. code::
+
+        <policy domain="coder" rights="read|write" pattern="PDF" />
 
 Migration to paperless-ng
 #########################
@@ -221,10 +368,10 @@ things have changed under the hood, so you need to adapt your setup depending on
 how you installed paperless. The important things to keep in mind are as follows.
 
 * Read the :ref:`changelog <paperless_changelog>` and take note of breaking changes.
-* It is recommended to use postgresql as the database now. If you want to continue
-  using SQLite, which is the default of paperless, use ``docker-compose.sqlite.yml``.
-  See :ref:`setup-sqlite_to_psql` for details on how to move your data from
-  sqlite to postgres.
+* You should decide if you want to stick with SQLite or want to migrate your database
+  to PostgreSQL. See :ref:`setup-sqlite_to_psql` for details on how to move your data from
+  SQLite to PostgreSQL. Both work fine with paperless. However, if you already have a
+  database server running for other services, you might as well use it for paperless as well.
 * The task scheduler of paperless, which is used to execute periodic tasks
   such as email checking and maintenance, requires a `redis`_ message broker
   instance. The docker-compose route takes care of that.
@@ -259,22 +406,31 @@ Migration to paperless-ng is then performed in a few simple steps:
         will be incompatible with the migrated volumes.
 
 4.  Copy the ``docker-compose.sqlite.yml`` file to ``docker-compose.yml``.
-    If you want to migrate to PostgreSQL, do that after you migrated your existing
+    If you want to switch to PostgreSQL, do that after you migrated your existing
     SQLite database.
 
 5.  Adjust ``docker-compose.yml`` and
     ``docker-compose.env`` to your needs.
     See `docker route`_ for details on which edits are advised.
 
-6.  Start paperless-ng.
+6.  Since ``docker-compose`` would just use the the old paperless image, we need to
+    manually build a new image:
 
-    .. code:: bash
+    .. code:: shell-session
 
-        $ docker-compose up
+        $ docker-compose build
 
-    If you see everything working (you should see some migrations getting
-    applied, for instance), you can gracefully stop paperless-ng with Ctrl-C
-    and then start paperless-ng as usual with
+7.  In order to find your existing documents with the new search feature, you need
+    to invoke a one-time operation that will create the search index:
+
+    .. code:: shell-session
+
+        $ docker-compose run --rm webserver document_index reindex
+    
+    This will migrate your database and create the search index. After that,
+    paperless will take care of maintaining the index by itself.
+
+8.  Start paperless-ng.
 
     .. code:: bash
 
@@ -282,11 +438,11 @@ Migration to paperless-ng is then performed in a few simple steps:
 
     This will run paperless in the background and automatically start it on system boot.
 
-7.  Paperless installed a permanent redirect to ``admin/`` in your browser. This
+9.  Paperless installed a permanent redirect to ``admin/`` in your browser. This
     redirect is still in place and prevents access to the new UI. Clear
     browsing cache in order to fix this.
 
-8.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
+10.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
 
 
 .. _setup-sqlite_to_psql:
@@ -299,7 +455,7 @@ management commands as below.
 
 .. caution::
 
-    Make sure that your sqlite database is migrated to the latest version.
+    Make sure that your SQLite database is migrated to the latest version.
     Starting paperless will make sure that this is the case. If your try to
     load data from an old database schema in SQLite into a newer database
     schema in PostgreSQL, you will run into trouble.
@@ -323,7 +479,7 @@ management commands as below.
             $ cd /path/to/paperless
             $ docker-compose run --rm webserver /bin/bash
         
-        This will lauch the container and initialize the PostgreSQL database.
+        This will launch the container and initialize the PostgreSQL database.
     
     b)  Without docker, open a shell in your virtual environment, switch to
         the ``src`` directory and create the database schema:
@@ -358,6 +514,35 @@ management commands as below.
 7.  Start paperless.
 
 
+Moving back to paperless
+========================
+
+Lets say you migrated to Paperless-ng and used it for a while, but decided that
+you don't like it and want to move back (If you do, send me a mail about what
+part you didn't like!), you can totally do that with a few simple steps.
+
+Paperless-ng modified the database schema slightly, however, these changes can
+be reverted while keeping your current data, so that your current data will
+be compatible with original Paperless.
+
+Execute this:
+
+.. code:: shell-session
+
+    $ cd /path/to/paperless
+    $ docker-compose run --rm webserver migrate documents 0023
+
+Or without docker:
+
+.. code:: shell-session
+
+    $ cd /path/to/paperless/src
+    $ python3 manage.py migrate documents 0023
+
+After that, you need to clear your cookies (Paperless-ng comes with updated
+dependencies that do cookie-processing differently) and probably your cache
+as well.
+
 .. _setup-less_powerful_devices:
 
 
@@ -367,20 +552,19 @@ Considerations for less powerful devices
 Paperless runs on Raspberry Pi. However, some things are rather slow on the Pi and 
 configuring some options in paperless can help improve performance immensely:
 
+*   Stick with SQLite to save some resources.
 *   Consider setting ``PAPERLESS_OCR_PAGES`` to 1, so that paperless will only OCR
     the first page of your documents.
 *   ``PAPERLESS_TASK_WORKERS`` and ``PAPERLESS_THREADS_PER_WORKER`` are configured
     to use all cores. The Raspberry Pi models 3 and up have 4 cores, meaning that
     paperless will use 2 workers and 2 threads per worker. This may result in
-    slugish response times during consumption, so you might want to lower these
+    sluggish response times during consumption, so you might want to lower these
     settings (example: 2 workers and 1 thread to always have some computing power
     left for other tasks).
-*   Keep ``PAPERLESS_OCR_ALWAYS`` at its default value 'false' and consider OCR'ing
+*   Keep ``PAPERLESS_OCR_MODE`` at its default value ``skip`` and consider OCR'ing
     your documents before feeding them into paperless. Some scanners are able to
-    do this!
-*   Lower ``PAPERLESS_CONVERT_DENSITY`` from its default value 300 to 200. This
-    will still result in rather accurate OCR, but will decrease consumption time
-    by quite a bit.
+    do this! You might want to even specify ``skip_noarchive`` to skip archive
+    file generation for already ocr'ed documents entirely.
 *   Set ``PAPERLESS_OPTIMIZE_THUMBNAILS`` to 'false' if you want faster consumption
     times. Thumbnails will be about 20% larger.
 

docs/troubleshooting.rst

@@ -29,75 +29,23 @@ Check for the following issues:
 Consumer fails to pickup any new files
 ######################################
 
-If you notice, that the consumer will only pickup files in the consumption
+If you notice that the consumer will only pickup files in the consumption
 directory at startup, but won't find any other files added later, check out
 the configuration file and enable filesystem polling with the setting
 ``PAPERLESS_CONSUMER_POLLING``.
 
+Operation not permitted
+#######################
 
-Consumer warns ``OCR for XX failed``
-####################################
+You might see errors such as:
 
-If you find the OCR accuracy to be too low, and/or the document consumer warns
-that ``OCR for XX failed, but we're going to stick with what we've got since
-FORGIVING_OCR is enabled``, then you might need to install the
-`Tesseract language files <http://packages.ubuntu.com/search?keywords=tesseract-ocr>`_
-marching your document's languages.
+.. code::
 
-As an example, if you are running Paperless from any Ubuntu or Debian
-box, and your documents are written in Spanish you may need to run::
+    chown: changing ownership of '../export': Operation not permitted
 
-    apt-get install -y tesseract-ocr-spa
+The container tries to set file ownership on the listed directories. This is
+required so that the user running paperless inside docker has write permissions
+to these folders. This happens when pointing these directories to NFS shares,
+for example.
 
-
-
-Consumer dies with ``convert: unable to extent pixel cache``
-############################################################
-
-During the consumption process, Paperless invokes ImageMagick's ``convert``
-program to translate the source document into something that the OCR engine can
-understand and this can burn a Very Large amount of memory if the original
-document is rather long.  Similarly, if your system doesn't have a lot of
-memory to begin with (ie. a Raspberry Pi), then this can happen for even
-medium-sized documents.
-
-The solution is to tell ImageMagick *not* to Use All The RAM, as is its
-default, and instead tell it to used a fixed amount.  ``convert`` will then
-break up the job into hundreds of individual files and use them to slowly
-compile the finished image.  Simply set ``PAPERLESS_CONVERT_MEMORY_LIMIT`` in
-``/etc/paperless.conf`` to something like ``32000000`` and you'll limit
-``convert`` to 32MB.  Fiddle with this value as you like.
-
-**HOWEVER**: Simply setting this value may not be enough on system where
-``/tmp`` is mounted as tmpfs, as this is where ``convert`` will write its
-temporary files.  In these cases (most Systemd machines), you need to tell
-ImageMagick to use a different space for its scratch work.  You do this by
-setting ``PAPERLESS_CONVERT_TMPDIR`` in ``/etc/paperless.conf`` to somewhere
-that's actually on a physical disk (and writable by the user running
-Paperless), like ``/var/tmp/paperless`` or ``/home/my_user/tmp`` in a pinch.
-
-
-DecompressionBombWarning and/or no text in the OCR output
-#########################################################
-
-Some users have had issues using Paperless to consume PDFs that were created
-by merging Very Large Scanned Images into one PDF.  If this happens to you,
-it's likely because the PDF you've created contains some very large pages
-(millions of pixels) and the process of converting the PDF to a OCR-friendly
-image is exploding.
-
-Typically, this happens because the scanned images are created with a high
-DPI and then rolled into the PDF with an assumed DPI of 72 (the default).
-The best solution then is to specify the DPI used in the scan in the
-conversion-to-PDF step.  So for example, if you scanned the original image
-with a DPI of 300, then merging the images into the single PDF with
-``convert`` should look like this:
-
-.. code:: bash
-
-    $ convert -density 300 *.jpg finished.pdf
-
-For more information on this and situations like it, you should take a look
-at `Issue #118`_ as that's where this tip originated.
-
-.. _Issue #118: https://github.com/the-paperless-project/paperless/issues/118
+Ensure that `chown` is possible on these directories.

docs/usage_overview.rst

@@ -5,13 +5,13 @@ Usage Overview
 Paperless is an application that manages your personal documents. With
 the help of a document scanner (see :ref:`scanners`), paperless transforms
 your wieldy physical document binders into a searchable archive and
-provices many utilities for finding and managing your documents.
+provides many utilities for finding and managing your documents.
 
 
 Terms and definitions
 #####################
 
-Paperless esentially consists of two different parts for managing your
+Paperless essentially consists of two different parts for managing your
 documents:
 
 * The *consumer* watches a specified folder and adds all documents in that
@@ -30,12 +30,12 @@ Each document has a couple of fields that you can assign to them:
   tag, however, a single document can also have multiple tags. This is not
   possible with folders. The reason folders are not implemented in paperless
   is simply that tags are much more versatile than folders.
-* A *document type* is used to demarkate the type of a document such as letter,
+* A *document type* is used to demarcate the type of a document such as letter,
   bank statement, invoice, contract, etc. It is used to identify what a document
   is about.
 * The *date added* of a document is the date the document was scanned into
   paperless. You cannot and should not change this date.
-* The *date created* of a document is the date the document was intially issued.
+* The *date created* of a document is the date the document was initially issued.
   This can be the date you bought a product, the date you signed a contract, or
   the date a letter was sent to you.
 * The *archive serial number* (short: ASN) of a document is the identifier of
@@ -57,8 +57,29 @@ Adding documents to paperless
 #############################
 
 Once you've got Paperless setup, you need to start feeding documents into it.
-Currently, there are three options: the consumption directory, IMAP (email), and
-HTTP POST.
+When adding documents to paperless, it will perform the following operations on
+your documents:
+
+1.  OCR the document, if it has no text. Digital documents usually have text,
+    and this step will be skipped for those documents.
+2.  Paperless will create an archiveable PDF/A document from your document.
+    If this document is coming from your scanner, it will have embedded selectable text.
+3.  Paperless performs automatic matching of tags, correspondents and types on the
+    document before storing it in the database.
+
+.. hint::
+
+    This process can be configured to fit your needs. If you don't want paperless
+    to create archived versions for digital documents, you can configure that by
+    configuring ``PAPERLESS_OCR_MODE=skip_noarchive``. Please read the 
+    :ref:`relevant section in the documentation <configuration-ocr>`.
+
+.. note::
+
+    No matter which options you choose, Paperless will always store the original
+    document that it found in the consumption directory or in the mail and
+    will never overwrite that document. Archived versions are stored alongside the
+    original versions.
 
 
 The consumption directory
@@ -82,6 +103,23 @@ files from the scanner.  Typically, you're looking at an FTP server like
 
 .. TODO: hyperref to configuration of the location of this magic folder.
 
+Dashboard upload
+================
+
+The dashboard has a file drop field to upload documents to paperless. Simply drag a file
+onto this field or select a file with the file dialog. Multiple files are supported.
+
+
+Mobile upload
+=============
+
+The mobile app over at `<https://github.com/qcasey/paperless_share>`_ allows Android users
+to share any documents with paperless. This can be combined with any of the mobile
+scanning apps out there, such as Office Lens.
+
+Furthermore, there is the  `Paperless App <https://github.com/bauerj/paperless_app>`_ as well,
+which no only has document upload, but also document editing and browsing.
+
 .. _usage-email:
 
 IMAP (Email)
@@ -131,7 +169,7 @@ These are as follows:
 
     With the correct set of rules, you can completely automate your email documents.
     Create rules for every correspondent you receive digital documents from and
-    paperless will read them automatically. The default acion "mark as read" is
+    paperless will read them automatically. The default action "mark as read" is
     pretty tame and will not cause any damage or data loss whatsoever.
 
     You can also setup a special folder in your mail account for paperless and use
@@ -156,6 +194,119 @@ REST API
 
 You can also submit a document using the REST API, see :ref:`api-file_uploads` for details.
 
+.. _basic-searching:
+
+
+Best practices
+##############
+
+Paperless offers a couple tools that help you organize your document collection. However,
+it is up to you to use them in a way that helps you organize documents and find specific
+documents when you need them. This section offers a couple ideas for managing your collection.
+
+Document types allow you to classify documents according to what they are. You can define
+types such as "Receipt", "Invoice", or "Contract". If you used to collect all your receipts
+in a single binder, you can recreate that system in paperless by defining a document type,
+assigning documents to that type and then filtering by that type to only see all receipts.
+
+Not all documents need document types. Sometimes its hard to determine what the type of a
+document is or it is hard to justify creating a document type that you only need once or twice.
+This is okay. As long as the types you define help you organize your collection in the way
+you want, paperless is doing its job.
+
+Tags can be used in many different ways. Think of tags are more versatile folders or binders.
+If you have a binder for documents related to university / your car or health care, you can
+create these binders in paperless by creating tags and assigning them to relevant documents.
+Just as with documents, you can filter the document list by tags and only see documents of
+a certain topic.
+
+With physical documents, you'll often need to decide which folder the document belongs to.
+The advantage of tags over folders and binders is that a single document can have multiple
+tags. A physical document cannot magically appear in two different folders, but with tags,
+this is entirely possible.
+
+.. hint::
+
+  This can be used in many different ways. One example: Imagine you're working on a particular
+  task, such as signing up for university. Usually you'll need to collect a bunch of different
+  documents that are already sorted into various folders. With the tag system of paperless,
+  you can create a new group of documents that are relevant to this task without destroying
+  the already existing organization. When you're done with the task, you could delete the
+  tag again, which would be equal to sorting documents back into the folder they belong into.
+  Or keep the tag, up to you.
+
+All of the logic above applies to correspondents as well. Attach them to documents if you
+feel that they help you organize your collection.
+
+When you've started organizing your documents, create a couple saved views for document collections
+you regularly access. This is equal to having labeled physical binders on your desk, except
+that these saved views are dynamic and simply update themselves as you add documents to the system.
+
+Here are a couple examples of tags and types that you could use in your collection.
+
+* An ``inbox`` tag for newly added documents that you haven't manually edited yet.
+* A tag ``car`` for everything car related (repairs, registration, insurance, etc)
+* A tag ``todo`` for documents that you still need to do something with, such as reply, or
+  perform some task online.
+* A tag ``bank account x`` for all bank statement related to that account.
+* A tag ``mail`` for anything that you added to paperless via its mail processing capabilities.
+* A tag ``missing_metadata`` when you still need to add some metadata to a document, but can't
+  or don't want to do this right now.
+
+Searching
+#########
+
+Paperless offers an extensive searching mechanism that is designed to allow you to quickly
+find a document you're looking for (for example, that thing that just broke and you bought
+a couple months ago, that contract you signed 8 years ago).
+
+When you search paperless for a document, it tries to match this query against your documents.
+Paperless will look for matching documents by inspecting their content, title, correspondent,
+type and tags. Paperless returns a scored list of results, so that documents matching your query
+better will appear further up in the search results.
+
+By default, paperless returns only documents which contain all words typed in the search bar.
+However, paperless also offers advanced search syntax if you want to drill down the results
+further.
+
+Matching documents with logical expressions:
+
+.. code::
+
+  shopname AND (product1 OR product2)
+
+Matching specific tags, correspondents or types:
+
+.. code::
+
+  type:invoice tag:unpaid
+  correspondent:university certificate
+
+Matching dates:
+
+.. code::
+  
+  created:[2005 to 2009]
+  added:yesterday
+  modified:today
+
+Matching inexact words:
+
+.. code::
+
+  produ*name
+
+.. note::
+
+  Inexact terms are hard for search indexes. These queries might take a while to execute. That's why paperless offers
+  auto complete and query correction.
+
+All of these constructs can be combined as you see fit.
+If you want to learn more about the query language used by paperless, paperless uses Whoosh's default query language. 
+Head over to `Whoosh query language <https://whoosh.readthedocs.io/en/latest/querylang.html>`_.
+For details on what date parsing utilities are available, see
+`Date parsing <https://whoosh.readthedocs.io/en/latest/dates.html#parsing-date-queries>`_.
+ 
 
 .. _usage-recommended_workflow:
 
@@ -182,7 +333,7 @@ Processing of the physical documents
 ====================================
 
 Keep a physical inbox. Whenever you receive a document that you need to
-archive, put it into your inbox. Regulary, do the following for all documents
+archive, put it into your inbox. Regularly, do the following for all documents
 in your inbox:
 
 1.  For each document, decide if you need to keep the document in physical
@@ -217,18 +368,24 @@ Once you have scanned in a document, proceed in paperless as follows.
 
 1.  If the document has an ASN, assign the ASN to the document.
 2.  Assign a correspondent to the document (i.e., your employer, bank, etc)
-    This isnt strictly necessary but helps in finding a document when you need
+    This isn't strictly necessary but helps in finding a document when you need
     it.
 3.  Assign a document type (i.e., invoice, bank statement, etc) to the document
-    This isnt strictly necessary but helps in finding a document when you need
+    This isn't strictly necessary but helps in finding a document when you need
     it.
 4.  Assign a proper title to the document (the name of an item you bought, the
     subject of the letter, etc)
-5.  Check that the date of the document is corrent. Paperless tries to read
+5.  Check that the date of the document is correct. Paperless tries to read
     the date from the content of the document, but this fails sometimes if the
     OCR is bad or multiple dates appear on the document.
 6.  Remove inbox tags from the documents.
 
+.. hint::
+    
+    You can setup manual matching rules for your correspondents and tags and
+    paperless will assign them automatically. After consuming a couple documents,
+    you can even ask paperless to *learn* when to assign tags and correspondents
+    by itself. For details on this feature, see :ref:`advanced-matching`.
 
 Task management
 ===============

paperless.conf.example

@@ -29,20 +29,27 @@
 #PAPERLESS_CORS_ALLOWED_HOSTS=localhost:8080,example.com,localhost:8000
 #PAPERLESS_FORCE_SCRIPT_NAME=
 #PAPERLESS_STATIC_URL=/static/
+#PAPERLESS_AUTO_LOGIN_USERNAME=
+#PAPERLESS_COOKIE_PREFIX=
+
+# OCR settings
+
+#PAPERLESS_OCR_LANGUAGE=eng
+#PAPERLESS_OCR_MODE=skip
+#PAPERLESS_OCR_OUTPUT_TYPE=pdfa
+#PAPERLESS_OCR_PAGES=1
+#PAPERLESS_OCR_IMAGE_DPI=300
+#PAPERLESS_OCR_USER_ARG={}
+#PAPERLESS_CONVERT_MEMORY_LIMIT=0
+#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
 
 # Software tweaks
 
 #PAPERLESS_TASK_WORKERS=1
 #PAPERLESS_THREADS_PER_WORKER=1
 #PAPERLESS_TIME_ZONE=UTC
-#PAPERLESS_OCR_PAGES=1
-#PAPERLESS_OCR_LANGUAGE=eng
-#PAPERLESS_OCR_ALWAYS=false
 #PAPERLESS_CONSUMER_POLLING=10
 #PAPERLESS_CONSUMER_DELETE_DUPLICATES=false
-#PAPERLESS_CONVERT_MEMORY_LIMIT=0
-#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
-#PAPERLESS_CONVERT_DENSITY=300
 #PAPERLESS_OPTIMIZE_THUMBNAILS=true
 #PAPERLESS_POST_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_FILENAME_DATE_ORDER=YMD
@@ -52,5 +59,4 @@
 
 #PAPERLESS_CONVERT_BINARY=/usr/bin/convert
 #PAPERLESS_GS_BINARY=/usr/bin/gs
-#PAPERLESS_UNPAPER_BINARY=/usr/bin/unpaper
 #PAPERLESS_OPTIPNG_BINARY=/usr/bin/optipng

scripts/make-release.sh

@@ -1,5 +1,20 @@
 #!/bin/bash
 
+# Release checklist
+# - wait for travis build.
+# adjust src/paperless/version.py
+# changelog in the documentation
+# adjust versions in docker/hub/*
+# adjust version in src-ui/src/environments/prod
+# If docker-compose was modified: all compose files are the same.
+
+# Steps:
+# run release script "dev", push
+# if it works: new tag, merge into master
+# on master: make release "lastest", push
+# on master: make release "version-tag", push
+# publish release files
+
 set -e
 
 
@@ -28,6 +43,7 @@ fi
 mkdir "$PAPERLESS_DIST"
 mkdir "$PAPERLESS_DIST_APP"
 mkdir "$PAPERLESS_DIST_APP/docker"
+mkdir "$PAPERLESS_DIST_APP/scripts"
 mkdir "$PAPERLESS_DIST_DOCKERFILES"
 
 # setup dependencies.
@@ -90,6 +106,11 @@ cp "$PAPERLESS_ROOT/docker/gunicorn.conf.py" "$PAPERLESS_DIST_APP/docker/"
 cp "$PAPERLESS_ROOT/docker/imagemagick-policy.xml" "$PAPERLESS_DIST_APP/docker/"
 cp "$PAPERLESS_ROOT/docker/supervisord.conf" "$PAPERLESS_DIST_APP/docker/"
 
+# auxiliary files for bare metal installs
+cp "$PAPERLESS_ROOT/scripts/paperless-webserver.service" "$PAPERLESS_DIST_APP/scripts/"
+cp "$PAPERLESS_ROOT/scripts/paperless-consumer.service" "$PAPERLESS_DIST_APP/scripts/"
+cp "$PAPERLESS_ROOT/scripts/paperless-scheduler.service" "$PAPERLESS_DIST_APP/scripts/"
+
 # try to make the docker build.
 
 cd "$PAPERLESS_DIST_APP"

scripts/paperless-consumer.service

@@ -1,10 +1,12 @@
 [Unit]
 Description=Paperless consumer
+Requires=redis.service
 
 [Service]
 User=paperless
 Group=paperless
-ExecStart=/home/paperless/project/virtualenv/bin/python /home/paperless/project/src/manage.py document_consumer
+WorkingDirectory=/opt/paperless/src
+ExecStart=python3 manage.py document_consumer
 
 [Install]
 WantedBy=multi-user.target

scripts/paperless-scheduler.service

@@ -0,0 +1,12 @@
+[Unit]
+Description=Paperless consumer
+Requires=redis.service
+
+[Service]
+User=paperless
+Group=paperless
+WorkingDirectory=/opt/paperless/src
+ExecStart=python3 manage.py qcluster
+
+[Install]
+WantedBy=multi-user.target

scripts/paperless-webserver.service

@@ -2,11 +2,13 @@
 Description=Paperless webserver
 After=network.target
 Wants=network.target
+Requires=redis.service
 
 [Service]
 User=paperless
 Group=paperless
-ExecStart=/home/paperless/project/virtualenv/bin/gunicorn --pythonpath=/home/paperless/project/src paperless.wsgi -w 2
+WorkingDirectory=/opt/paperless/src
+ExecStart=/opt/paperless/.local/bin/gunicorn paperless.wsgi -w 2 -b 0.0.0.0:8000
 
 [Install]
 WantedBy=multi-user.target

src-ui/package-lock.json

@@ -2215,6 +2215,11 @@
       "integrity": "sha512-UV1/ZJMC+HcP902wWdpC43cAcGu0IQk/I5bXjP2aSuCjsk3cE74mDvFrLKga7oDC170ugOAYBwfT4DSQW3akDA==",
       "dev": true
     },
+    "@types/pdfjs-dist": {
+      "version": "2.1.7",
+      "resolved": "https://registry.npmjs.org/@types/pdfjs-dist/-/pdfjs-dist-2.1.7.tgz",
+      "integrity": "sha512-nQIwcPUhkAIyn7x9NS0lR/qxYfd5unRtfGkMjvpgF4Sh28IXftRymaNmFKTTdejDNY25NDGSIyjwj/BRwAPexg=="
+    },
     "@types/q": {
       "version": "1.5.4",
       "resolved": "https://registry.npmjs.org/@types/q/-/q-1.5.4.tgz",
@@ -3023,6 +3028,16 @@
       "integrity": "sha512-1Yj8h9Q+QDF5FzhMs/c9+6UntbD5MkRfRwac8DoEm9ZfUBZ7tZ55YcGVAzEe4bXsdQHEk+s9S5wsOKVdZrw0tQ==",
       "dev": true
     },
+    "bindings": {
+      "version": "1.5.0",
+      "resolved": "https://registry.npmjs.org/bindings/-/bindings-1.5.0.tgz",
+      "integrity": "sha512-p2q/t/mhvuOj/UeLlV6566GD/guowlr0hHxClI0W9m7MWYkL1F0hLo+0Aexs9HSPCtR1SXQ0TD3MMKrXZajbiQ==",
+      "dev": true,
+      "optional": true,
+      "requires": {
+        "file-uri-to-path": "1.0.0"
+      }
+    },
     "blob": {
       "version": "0.0.5",
       "resolved": "https://registry.npmjs.org/blob/-/blob-0.0.5.tgz",
@@ -5508,6 +5523,13 @@
         "schema-utils": "^2.6.5"
       }
     },
+    "file-uri-to-path": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/file-uri-to-path/-/file-uri-to-path-1.0.0.tgz",
+      "integrity": "sha512-0Zt+s3L7Vf1biwWZ29aARiVYLx7iMGnEUl9x33fbB/j3jR81u/O2LbqK+Bm1CDSNDKVtJ/YjwY7TUd5SkeLQLw==",
+      "dev": true,
+      "optional": true
+    },
     "fill-range": {
       "version": "7.0.1",
       "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.0.1.tgz",
@@ -8208,6 +8230,13 @@
       "integrity": "sha512-nnbWWOkoWyUsTjKrhgD0dcz22mdkSnpYqbEjIm2nhwhuxlSkpywJmBo8h0ZqJdkp73mb90SssHkN4rsRaBAfAA==",
       "dev": true
     },
+    "nan": {
+      "version": "2.14.2",
+      "resolved": "https://registry.npmjs.org/nan/-/nan-2.14.2.tgz",
+      "integrity": "sha512-M2ufzIiINKCuDfBSAUr1vWQ+vuVcA9kqx8JJUsbQi6yf1uGRyb7HfpdfUr5qLXf3B/t8dPvcjhKMmlfnP47EzQ==",
+      "dev": true,
+      "optional": true
+    },
     "nanomatch": {
       "version": "1.2.13",
       "resolved": "https://registry.npmjs.org/nanomatch/-/nanomatch-1.2.13.tgz",
@@ -8260,6 +8289,23 @@
         "moment": "2.18.1"
       }
     },
+    "ng2-pdf-viewer": {
+      "version": "6.3.2",
+      "resolved": "https://registry.npmjs.org/ng2-pdf-viewer/-/ng2-pdf-viewer-6.3.2.tgz",
+      "integrity": "sha512-H2tBhDd+Lq6CUzK2g54HsCcZDR2wTn1sDjYqKY3yF0Ydasl2R5ppCKynZBU/zge4EKvmHglJI120FbQMpJKDYQ==",
+      "requires": {
+        "@types/pdfjs-dist": "^2.1.4",
+        "pdfjs-dist": "^2.4.456",
+        "tslib": "^1.10.0"
+      },
+      "dependencies": {
+        "tslib": {
+          "version": "1.14.1",
+          "resolved": "https://registry.npmjs.org/tslib/-/tslib-1.14.1.tgz",
+          "integrity": "sha512-Xni35NKzjgMrwevysHTCArtLDpPvye8zV/0E4EyYn43P7/7qvQwPh9BGkHewbMulVntbigmcT7rdX3BNo9wRJg=="
+        }
+      }
+    },
     "ngx-cookie-service": {
       "version": "10.1.1",
       "resolved": "https://registry.npmjs.org/ngx-cookie-service/-/ngx-cookie-service-10.1.1.tgz",
@@ -9270,6 +9316,11 @@
         "sha.js": "^2.4.8"
       }
     },
+    "pdfjs-dist": {
+      "version": "2.5.207",
+      "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-2.5.207.tgz",
+      "integrity": "sha512-xGDUhnCYPfHy+unMXCLCJtlpZaaZ17Ew3WIL0tnSgKFUZXHAPD49GO9xScyszSsQMoutNDgRb+rfBXIaX/lJbw=="
+    },
     "performance-now": {
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/performance-now/-/performance-now-2.1.0.tgz",
@@ -13228,7 +13279,11 @@
           "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-1.2.13.tgz",
           "integrity": "sha512-oWb1Z6mkHIskLzEJ/XWX0srkpkTQ7vaopMQkyaEIoq0fmtFVxOthb8cCxeT+p3ynTdkk/RZwbgG4brR5BeWECw==",
           "dev": true,
-          "optional": true
+          "optional": true,
+          "requires": {
+            "bindings": "^1.5.0",
+            "nan": "^2.12.1"
+          }
         },
         "glob-parent": {
           "version": "3.1.0",
@@ -13832,7 +13887,11 @@
           "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-1.2.13.tgz",
           "integrity": "sha512-oWb1Z6mkHIskLzEJ/XWX0srkpkTQ7vaopMQkyaEIoq0fmtFVxOthb8cCxeT+p3ynTdkk/RZwbgG4brR5BeWECw==",
           "dev": true,
-          "optional": true
+          "optional": true,
+          "requires": {
+            "bindings": "^1.5.0",
+            "nan": "^2.12.1"
+          }
         },
         "glob-parent": {
           "version": "3.1.0",

src-ui/package.json

@@ -23,6 +23,7 @@
     "@ng-bootstrap/ng-bootstrap": "^8.0.0",
     "bootstrap": "^4.5.0",
     "ng-bootstrap": "^1.6.3",
+    "ng2-pdf-viewer": "^6.3.2",
     "ngx-cookie-service": "^10.1.1",
     "ngx-file-drop": "^10.0.0",
     "ngx-infinite-scroll": "^9.1.0",

src-ui/src/app/app.module.ts

@@ -14,20 +14,22 @@ import { LogsComponent } from './components/manage/logs/logs.component';
 import { SettingsComponent } from './components/manage/settings/settings.component';
 import { FormsModule, ReactiveFormsModule } from '@angular/forms';
 import { DatePipe } from '@angular/common';
-import { SafePipe } from './pipes/safe.pipe';
 import { NotFoundComponent } from './components/not-found/not-found.component';
 import { CorrespondentListComponent } from './components/manage/correspondent-list/correspondent-list.component';
-import { DeleteDialogComponent } from './components/common/delete-dialog/delete-dialog.component';
+import { ConfirmDialogComponent } from './components/common/confirm-dialog/confirm-dialog.component';
 import { CorrespondentEditDialogComponent } from './components/manage/correspondent-list/correspondent-edit-dialog/correspondent-edit-dialog.component';
 import { TagEditDialogComponent } from './components/manage/tag-list/tag-edit-dialog/tag-edit-dialog.component';
 import { DocumentTypeEditDialogComponent } from './components/manage/document-type-list/document-type-edit-dialog/document-type-edit-dialog.component';
 import { TagComponent } from './components/common/tag/tag.component';
 import { SearchComponent } from './components/search/search.component';
-import { ResultHightlightComponent } from './components/search/result-hightlight/result-hightlight.component';
+import { ResultHighlightComponent } from './components/search/result-highlight/result-highlight.component';
 import { PageHeaderComponent } from './components/common/page-header/page-header.component';
 import { AppFrameComponent } from './components/app-frame/app-frame.component';
 import { ToastsComponent } from './components/common/toasts/toasts.component';
 import { FilterEditorComponent } from './components/filter-editor/filter-editor.component';
+import { FilterDropdownComponent } from './components/filter-editor/filter-dropdown/filter-dropdown.component';
+import { FilterDropdownButtonComponent } from './components/filter-editor/filter-dropdown/filter-dropdown-button/filter-dropdown-button.component';
+import { FilterDropdownDateComponent } from './components/filter-editor/filter-dropdown-date/filter-dropdown-date.component';
 import { DocumentCardLargeComponent } from './components/document-list/document-card-large/document-card-large.component';
 import { DocumentCardSmallComponent } from './components/document-list/document-card-small/document-card-small.component';
 import { NgxFileDropModule } from 'ngx-file-drop';
@@ -45,6 +47,13 @@ import { SavedViewWidgetComponent } from './components/dashboard/widgets/saved-v
 import { StatisticsWidgetComponent } from './components/dashboard/widgets/statistics-widget/statistics-widget.component';
 import { UploadFileWidgetComponent } from './components/dashboard/widgets/upload-file-widget/upload-file-widget.component';
 import { WidgetFrameComponent } from './components/dashboard/widgets/widget-frame/widget-frame.component';
+import { PdfViewerModule } from 'ng2-pdf-viewer';
+import { WelcomeWidgetComponent } from './components/dashboard/widgets/welcome-widget/welcome-widget.component';
+import { YesNoPipe } from './pipes/yes-no.pipe';
+import { FileSizePipe } from './pipes/file-size.pipe';
+import { FilterPipe } from './pipes/filter.pipe';
+import { DocumentTitlePipe } from './pipes/document-title.pipe';
+import { MetadataCollapseComponent } from './components/document-detail/metadata-collapse/metadata-collapse.component';
 
 @NgModule({
   declarations: [
@@ -57,19 +66,21 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     DocumentTypeListComponent,
     LogsComponent,
     SettingsComponent,
-    SafePipe,
     NotFoundComponent,
     CorrespondentEditDialogComponent,
-    DeleteDialogComponent,
+    ConfirmDialogComponent,
     TagEditDialogComponent,
     DocumentTypeEditDialogComponent,
     TagComponent,
     SearchComponent,
-    ResultHightlightComponent,
+    ResultHighlightComponent,
     PageHeaderComponent,
     AppFrameComponent,
     ToastsComponent,
     FilterEditorComponent,
+    FilterDropdownComponent,
+    FilterDropdownButtonComponent,
+    FilterDropdownDateComponent,
     DocumentCardLargeComponent,
     DocumentCardSmallComponent,
     TextComponent,
@@ -82,7 +93,13 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     SavedViewWidgetComponent,
     StatisticsWidgetComponent,
     UploadFileWidgetComponent,
-    WidgetFrameComponent
+    WidgetFrameComponent,
+    WelcomeWidgetComponent,
+    YesNoPipe,
+    FileSizePipe,
+    FilterPipe,
+    DocumentTitlePipe,
+    MetadataCollapseComponent
   ],
   imports: [
     BrowserModule,
@@ -92,7 +109,8 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     FormsModule,
     ReactiveFormsModule,
     NgxFileDropModule,
-    InfiniteScrollModule
+    InfiniteScrollModule,
+    PdfViewerModule
   ],
   providers: [
     DatePipe,
@@ -100,7 +118,9 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
       provide: HTTP_INTERCEPTORS,
       useClass: CsrfInterceptor,
       multi: true
-    }
+    },
+    FilterPipe,
+    DocumentTitlePipe
   ],
   bootstrap: [AppComponent]
 })

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -17,6 +17,11 @@
 <div class="container-fluid">
   <div class="row">
     <nav id="sidebarMenu" class="col-md-3 col-lg-2 d-md-block bg-light sidebar collapse" [ngbCollapse]="isMenuCollapsed">
+
+      <div style="position: absolute; bottom: 0; left: 0;" class="text-muted p-1">
+        {{versionString}}
+      </div>
+
       <div class="sidebar-sticky pt-3">
         <ul class="nav flex-column">
           <li class="nav-item">
@@ -37,16 +42,16 @@
           </li>
         </ul>
 
-        <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted" *ngIf='viewConfigService.getSideBarConfigs().length > 0'>
+        <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted" *ngIf='savedViewService.sidebarViews.length > 0'>
           <span>Saved views</span>
         </h6>
         <ul class="nav flex-column mb-2">
-          <li class="nav-item w-100" *ngFor='let config of viewConfigService.getSideBarConfigs()'>
-            <a class="nav-link text-truncate" routerLink="view/{{config.id}}" routerLinkActive="active" (click)="closeMenu()">
+          <li class="nav-item w-100" *ngFor="let view of savedViewService.sidebarViews">
+            <a class="nav-link text-truncate" routerLink="view/{{view.id}}" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#funnel"/>
               </svg>
-              {{config.title}}
+              {{view.name}}
             </a>
           </li>
         </ul>
@@ -60,7 +65,7 @@
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#file-text"/>
               </svg>
-              {{d.title}}
+              {{d.title | documentTitle}}
             </a>
           </li>
           <li class="nav-item w-100" *ngIf="openDocuments.length > 1">
@@ -132,7 +137,7 @@
         </h6>
         <ul class="nav flex-column mb-2">
           <li class="nav-item">
-            <a class="nav-link" href="https://paperless-ng.readthedocs.io/en/latest/">
+            <a class="nav-link" target="_blank" rel="noopener noreferrer" href="https://paperless-ng.readthedocs.io/en/latest/">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#question-circle"/>
               </svg>
@@ -140,7 +145,7 @@
             </a>
           </li>
           <li class="nav-item">
-            <a class="nav-link" href="https://github.com/jonaswinkler/paperless-ng">
+            <a class="nav-link" target="_blank" rel="noopener noreferrer" href="https://github.com/jonaswinkler/paperless-ng">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#link"/>
               </svg>

src-ui/src/app/components/app-frame/app-frame.component.scss

@@ -50,6 +50,7 @@
 
 .sidebar .nav-link.active {
   color: $primary;
+  font-weight: bold;
 }
 
 .sidebar .nav-link:hover .sidebaricon,

src-ui/src/app/components/app-frame/app-frame.component.ts

@@ -5,8 +5,9 @@ import { from, Observable, Subscription } from 'rxjs';
 import { debounceTime, distinctUntilChanged, map, switchMap } from 'rxjs/operators';
 import { PaperlessDocument } from 'src/app/data/paperless-document';
 import { OpenDocumentsService } from 'src/app/services/open-documents.service';
+import { SavedViewService } from 'src/app/services/rest/saved-view.service';
 import { SearchService } from 'src/app/services/rest/search.service';
-import { SavedViewConfigService } from 'src/app/services/saved-view-config.service';
+import { environment } from 'src/environments/environment';
 import { DocumentDetailComponent } from '../document-detail/document-detail.component';
   
 @Component({
@@ -21,10 +22,12 @@ export class AppFrameComponent implements OnInit, OnDestroy {
     private activatedRoute: ActivatedRoute,
     private openDocumentsService: OpenDocumentsService,
     private searchService: SearchService,
-    public viewConfigService: SavedViewConfigService
+    public savedViewService: SavedViewService
     ) {
   }
 
+  versionString = `${environment.appTitle} ${environment.version}`
+
   isMenuCollapsed: boolean = true
 
   closeMenu() {
@@ -90,7 +93,9 @@ export class AppFrameComponent implements OnInit, OnDestroy {
   }
 
   ngOnDestroy() {
-    this.openDocumentsSubscription.unsubscribe()
+    if (this.openDocumentsSubscription) {
+      this.openDocumentsSubscription.unsubscribe()
+    }
   }
 
 }

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.html

@@ -5,10 +5,10 @@
       </button>
     </div>
     <div class="modal-body">
-      <p><b>{{message}}</b></p>
-      <p *ngIf="message2">{{message2}}</p>
+      <p *ngIf="messageBold"><b>{{messageBold}}</b></p>
+      <p *ngIf="message">{{message}}</p>
     </div>
     <div class="modal-footer">
       <button type="button" class="btn btn-outline-dark" (click)="cancelClicked()">Cancel</button>
-      <button type="button" class="btn btn-danger" (click)="deleteClicked.emit()">Delete</button>
+      <button type="button" class="btn" [class]="btnClass" (click)="confirmClicked.emit()">{{btnCaption}}</button>
     </div>

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.spec.ts

@@ -1,20 +1,20 @@
 import { ComponentFixture, TestBed } from '@angular/core/testing';
 
-import { DeleteDialogComponent } from './delete-dialog.component';
+import { ConfirmDialogComponent } from './confirm-dialog.component';
 
-describe('DeleteDialogComponent', () => {
-  let component: DeleteDialogComponent;
-  let fixture: ComponentFixture<DeleteDialogComponent>;
+describe('ConfirmDialogComponent', () => {
+  let component: ConfirmDialogComponent;
+  let fixture: ComponentFixture<ConfirmDialogComponent>;
 
   beforeEach(async () => {
     await TestBed.configureTestingModule({
-      declarations: [ DeleteDialogComponent ]
+      declarations: [ ConfirmDialogComponent ]
     })
     .compileComponents();
   });
 
   beforeEach(() => {
-    fixture = TestBed.createComponent(DeleteDialogComponent);
+    fixture = TestBed.createComponent(ConfirmDialogComponent);
     component = fixture.componentInstance;
     fixture.detectChanges();
   });

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.ts

@@ -0,0 +1,37 @@
+import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap';
+
+@Component({
+  selector: 'app-confirm-dialog',
+  templateUrl: './confirm-dialog.component.html',
+  styleUrls: ['./confirm-dialog.component.scss']
+})
+export class ConfirmDialogComponent implements OnInit {
+
+  constructor(public activeModal: NgbActiveModal) { }
+
+  @Output()
+  public confirmClicked = new EventEmitter()
+
+  @Input()
+  title = "Confirmation"
+
+  @Input()
+  messageBold
+
+  @Input()
+  message
+
+  @Input()
+  btnClass = "btn-primary"
+
+  @Input()
+  btnCaption = "Confirm"
+
+  ngOnInit(): void {
+  }
+
+  cancelClicked() {
+    this.activeModal.close()
+  }
+}

src-ui/src/app/components/common/delete-dialog/delete-dialog.component.ts

@@ -1,31 +0,0 @@
-import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
-import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap';
-
-@Component({
-  selector: 'app-delete-dialog',
-  templateUrl: './delete-dialog.component.html',
-  styleUrls: ['./delete-dialog.component.scss']
-})
-export class DeleteDialogComponent implements OnInit {
-
-  constructor(public activeModal: NgbActiveModal) { }
-
-  @Output()
-  public deleteClicked = new EventEmitter()
-
-  @Input()
-  title = "Delete confirmation"
-
-  @Input()
-  message = "Do you really want to delete this?"
-
-  @Input()
-  message2
-
-  ngOnInit(): void {
-  }
-
-  cancelClicked() {
-    this.activeModal.close()
-  }
-}

src-ui/src/app/components/common/input/abstract-input.ts

@@ -1,5 +1,5 @@
-import { Component, Directive, forwardRef, Input, OnInit } from '@angular/core';
-import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
+import { Directive, Input, OnInit } from '@angular/core';
+import { ControlValueAccessor } from '@angular/forms';
 import { v4 as uuidv4 } from 'uuid';
 
 @Directive()

src-ui/src/app/components/common/input/date-time/date-time.component.html

@@ -3,11 +3,10 @@
       <label for="created_date">{{titleDate}}</label>
       <input type="date" class="form-control" id="created_date" [(ngModel)]="dateValue" (change)="dateOrTimeChanged()">
   </div>
-  <div class="form-group col">
+  <div class="form-group col" *ngIf="titleTime">
       <label for="created_time">{{titleTime}}</label>
       <input type="time" class="form-control" id="created_time" [(ngModel)]="timeValue" (change)="dateOrTimeChanged()">
   </div>
-
 </div>
 
 

src-ui/src/app/components/common/input/date-time/date-time.component.ts

@@ -1,7 +1,6 @@
 import { formatDate } from '@angular/common';
 import { Component, forwardRef, Input, OnInit } from '@angular/core';
 import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
-import { AbstractInputComponent } from '../abstract-input';
 
 @Component({
   providers: [{
@@ -40,7 +39,7 @@ export class DateTimeComponent implements OnInit,ControlValueAccessor  {
   titleDate: string = "Date"
 
   @Input()
-  titleTime: string = "Time"
+  titleTime: string
 
   @Input()
   disabled: boolean = false

src-ui/src/app/components/common/input/select/select.component.ts

@@ -1,4 +1,4 @@
-import { Component, EventEmitter, forwardRef, Input, OnInit, Output } from '@angular/core';
+import { Component, EventEmitter, forwardRef, Input, Output } from '@angular/core';
 import { NG_VALUE_ACCESSOR } from '@angular/forms';
 import { AbstractInputComponent } from '../abstract-input';
 

src-ui/src/app/components/common/input/tags/tags.component.html

@@ -8,7 +8,7 @@
 
     <div class="input-group-append" ngbDropdown placement="top-right">
       <button class="btn btn-outline-secondary" type="button" ngbDropdownToggle></button>
-      <div ngbDropdownMenu class="scrollable-menu">
+      <div ngbDropdownMenu class="scrollable-menu shadow">
         <button type="button" *ngFor="let tag of tags" ngbDropdownItem (click)="addTag(tag.id)">
           <app-tag [tag]="tag"></app-tag>
         </button>

src-ui/src/app/components/common/input/tags/tags.component.ts

@@ -1,8 +1,6 @@
-import { ThrowStmt } from '@angular/compiler';
 import { Component, forwardRef, Input, OnInit } from '@angular/core';
 import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
 import { NgbModal } from '@ng-bootstrap/ng-bootstrap';
-import { Observable } from 'rxjs';
 import { TagEditDialogComponent } from 'src/app/components/manage/tag-list/tag-edit-dialog/tag-edit-dialog.component';
 import { PaperlessTag } from 'src/app/data/paperless-tag';
 import { TagService } from 'src/app/services/rest/tag.service';

src-ui/src/app/components/common/input/text/text.component.ts

@@ -1,6 +1,5 @@
-import { Component, forwardRef, Input, OnInit } from '@angular/core';
-import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
-import { v4 as uuidv4 } from 'uuid';
+import { Component, forwardRef } from '@angular/core';
+import { NG_VALUE_ACCESSOR } from '@angular/forms';
 import { AbstractInputComponent } from '../abstract-input';
 
 @Component({

src-ui/src/app/components/common/page-header/page-header.component.ts

@@ -1,21 +1,29 @@
-import { Component, Input, OnInit } from '@angular/core';
+import { Component, Input } from '@angular/core';
+import { Title } from '@angular/platform-browser';
+import { environment } from 'src/environments/environment';
 
 @Component({
   selector: 'app-page-header',
   templateUrl: './page-header.component.html',
   styleUrls: ['./page-header.component.scss']
 })
-export class PageHeaderComponent implements OnInit {
+export class PageHeaderComponent {
 
-  constructor() { }
+  constructor(private titleService: Title) { }
+
+  _title = ""
 
   @Input()
-  title: string = ""
+  set title(title: string) {
+    this._title = title
+    this.titleService.setTitle(`${this.title} - ${environment.appTitle}`)
+  }
+
+  get title() {
+    return this._title
+  }
 
   @Input()
   subTitle: string = ""
 
-  ngOnInit(): void {
-  }
-
 }

src-ui/src/app/components/common/tag/tag.component.html

@@ -1,2 +1,2 @@
 <span *ngIf="!clickable" class="badge" [style.background]="getColour().value" [style.color]="getColour().textColor">{{tag.name}}</span>
-<a [routerLink]="" *ngIf="clickable" class="badge" [style.background]="getColour().value" [style.color]="getColour().textColor">{{tag.name}}</a>
+<a [routerLink]="" [title]="linkTitle" *ngIf="clickable" class="badge" [style.background]="getColour().value" [style.color]="getColour().textColor">{{tag.name}}</a>

src-ui/src/app/components/common/tag/tag.component.ts

@@ -1,4 +1,4 @@
-import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
+import { Component, Input, OnInit } from '@angular/core';
 import { TAG_COLOURS, PaperlessTag } from 'src/app/data/paperless-tag';
 
 @Component({
@@ -14,10 +14,10 @@ export class TagComponent implements OnInit {
   tag: PaperlessTag
 
   @Input()
-  clickable: boolean = false
+  linkTitle: string = ""
 
-  @Output()
-  click = new EventEmitter()
+  @Input()
+  clickable: boolean = false
 
   ngOnInit(): void {
   }

src-ui/src/app/components/dashboard/dashboard.component.html

@@ -3,23 +3,19 @@
 </app-page-header>
 
 <div class='row'>
-  <div class="col-lg">
-    <app-widget-frame title="Saved views" *ngIf="savedViews.length == 0">
-      <p class="card-text">This space is reserved to display your saved views. Go to your documents and save a view
-        to have it displayed
-        here!</p>
-    </app-widget-frame>
+  <div class="col-lg-8">
+    <app-welcome-widget *ngIf="savedViews.length == 0"></app-welcome-widget>
 
     <ng-container *ngFor="let v of savedViews">
       <app-saved-view-widget [savedView]="v"></app-saved-view-widget>
     </ng-container>
 
   </div>
-  <div class="col-lg">
+  <div class="col-lg-4">
 
     <app-statistics-widget></app-statistics-widget>
 
     <app-upload-file-widget></app-upload-file-widget>
 
   </div>
-</div>
+</div>

src-ui/src/app/components/dashboard/dashboard.component.ts

@@ -1,5 +1,6 @@
 import { Component, OnInit } from '@angular/core';
-import { SavedViewConfigService } from 'src/app/services/saved-view-config.service';
+import { PaperlessSavedView } from 'src/app/data/paperless-saved-view';
+import { SavedViewService } from 'src/app/services/rest/saved-view.service';
 
 
 @Component({
@@ -10,13 +11,15 @@ import { SavedViewConfigService } from 'src/app/services/saved-view-config.servi
 export class DashboardComponent implements OnInit {
 
   constructor(
-    public savedViewConfigService: SavedViewConfigService) { }
+    private savedViewService: SavedViewService) { }
 
 
-  savedViews = []
+  savedViews: PaperlessSavedView[] = []
 
   ngOnInit(): void {
-    this.savedViews = this.savedViewConfigService.getDashboardConfigs()
+    this.savedViewService.listAll().subscribe(results => {
+      this.savedViews = results.results.filter(savedView => savedView.show_on_dashboard)
+    })
   }
 
 }

src-ui/src/app/components/dashboard/widgets/saved-view-widget/saved-view-widget.component.html

@@ -1,6 +1,9 @@
-<app-widget-frame [title]="savedView.title">
+<app-widget-frame [title]="savedView.name">
 
-  <table class="table table-sm table-hover table-borderless">
+  <a header-buttons [routerLink]="" (click)="showAll()">Show all</a>
+
+
+  <table content class="table table-sm table-hover table-borderless">
     <thead>
       <tr>
         <th>Created</th>
@@ -10,7 +13,7 @@
     <tbody>
       <tr *ngFor="let doc of documents" routerLink="/documents/{{doc.id}}">
         <td>{{doc.created | date}}</td>
-        <td>{{doc.title}}<app-tag [tag]="t" *ngFor="let t of doc.tags" class="ml-1"></app-tag>
+        <td>{{doc.title | documentTitle}}<app-tag [tag]="t" *ngFor="let t of doc.tags$ | async" class="ml-1"></app-tag>
       </tr>
     </tbody>
   </table>

src-ui/src/app/components/dashboard/widgets/saved-view-widget/saved-view-widget.component.ts

@@ -1,6 +1,8 @@
 import { Component, Input, OnInit } from '@angular/core';
+import { Router } from '@angular/router';
 import { PaperlessDocument } from 'src/app/data/paperless-document';
-import { SavedViewConfig } from 'src/app/data/saved-view-config';
+import { PaperlessSavedView } from 'src/app/data/paperless-saved-view';
+import { DocumentListViewService } from 'src/app/services/document-list-view.service';
 import { DocumentService } from 'src/app/services/rest/document.service';
 
 @Component({
@@ -10,17 +12,29 @@ import { DocumentService } from 'src/app/services/rest/document.service';
 })
 export class SavedViewWidgetComponent implements OnInit {
 
-  constructor(private documentService: DocumentService) { }
+  constructor(
+    private documentService: DocumentService,
+    private router: Router,
+    private list: DocumentListViewService) { }
   
   @Input()
-  savedView: SavedViewConfig
+  savedView: PaperlessSavedView
 
   documents: PaperlessDocument[] = []
 
   ngOnInit(): void {
-    this.documentService.list(1,10,this.savedView.sortField,this.savedView.sortDirection,this.savedView.filterRules).subscribe(result => {
+    this.documentService.list(1,10,this.savedView.sort_field, this.savedView.sort_reverse, this.savedView.filter_rules).subscribe(result => {
       this.documents = result.results
     })
   }
 
+  showAll() {
+    if (this.savedView.show_in_sidebar) {
+      this.router.navigate(['view', this.savedView.id])
+    } else {
+      this.list.load(this.savedView)
+      this.router.navigate(["documents"])
+      }
+  }
+
 }

src-ui/src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html

@@ -1,4 +1,6 @@
 <app-widget-frame title="Statistics">
-  <p class="card-text">Documents in inbox: {{statistics.documents_inbox}}</p>
-  <p class="card-text">Total documents: {{statistics.documents_total}}</p>
+  <ng-container content>
+    <p class="card-text">Documents in inbox: {{statistics.documents_inbox}}</p>
+    <p class="card-text">Total documents: {{statistics.documents_total}}</p>
+  </ng-container>
 </app-widget-frame>

src-ui/src/app/components/dashboard/widgets/upload-file-widget/upload-file-widget.component.html

@@ -1,15 +1,18 @@
 <app-widget-frame title="Upload new documents">
 
-  <form>
-    <ngx-file-drop 
-      dropZoneLabel="Drop documents here or" (onFileDrop)="dropped($event)"
-      (onFileOver)="fileOver($event)" (onFileLeave)="fileLeave($event)"
-      dropZoneClassName="bg-light card"
-      multiple="true"
-      contentClassName="justify-content-center d-flex align-items-center p-5"
-      [showBrowseBtn]=true
-      browseBtnClassName="btn btn-sm btn-outline-primary ml-2">
+  <div content>
+    <form>
+      <ngx-file-drop dropZoneLabel="Drop documents here or" (onFileDrop)="dropped($event)"
+        (onFileOver)="fileOver($event)" (onFileLeave)="fileLeave($event)" dropZoneClassName="bg-light card"
+        multiple="true" contentClassName="justify-content-center d-flex align-items-center p-5" [showBrowseBtn]=true
+        browseBtnClassName="btn btn-sm btn-outline-primary ml-2">
 
-    </ngx-file-drop>
-  </form>
+      </ngx-file-drop>
+    </form>
+    <div *ngIf="uploadVisible" class="mt-3">
+      <p>Uploading {{uploadStatus.length}} file(s)</p>
+      <ngb-progressbar [value]="loadedSum" [max]="totalSum" [striped]="true" [animated]="uploadStatus.length > 0">
+      </ngb-progressbar>
+    </div>
+  </div>
 </app-widget-frame>

src-ui/src/app/components/dashboard/widgets/upload-file-widget/upload-file-widget.component.ts

@@ -1,8 +1,15 @@
+import { HttpEventType } from '@angular/common/http';
 import { Component, OnInit } from '@angular/core';
 import { FileSystemFileEntry, NgxFileDropEntry } from 'ngx-file-drop';
 import { DocumentService } from 'src/app/services/rest/document.service';
 import { Toast, ToastService } from 'src/app/services/toast.service';
 
+
+interface UploadStatus {
+  loaded: number
+  total: number 
+}
+
 @Component({
   selector: 'app-upload-file-widget',
   templateUrl: './upload-file-widget.component.html',
@@ -16,26 +23,59 @@ export class UploadFileWidgetComponent implements OnInit {
   }
 
   public fileOver(event){
-    console.log(event);
   }
- 
+
   public fileLeave(event){
-    console.log(event);
   }
- 
+
+  uploadStatus: UploadStatus[] = []
+  completedFiles = 0
+
+  uploadVisible = false
+
+  get loadedSum() {
+    return this.uploadStatus.map(s => s.loaded).reduce((a,b) => a+b, this.completedFiles > 0 ? 1 : 0)
+  }
+
+  get totalSum() {
+    return this.uploadStatus.map(s => s.total).reduce((a,b) => a+b, 1)
+  }
+
   public dropped(files: NgxFileDropEntry[]) {
     for (const droppedFile of files) {
       if (droppedFile.fileEntry.isFile) {
-        const fileEntry = droppedFile.fileEntry as FileSystemFileEntry;
-        console.log(fileEntry)
+      let uploadStatusObject: UploadStatus = {loaded: 0, total: 1}
+      this.uploadStatus.push(uploadStatusObject)
+      this.uploadVisible = true
+
+      const fileEntry = droppedFile.fileEntry as FileSystemFileEntry;
         fileEntry.file((file: File) => {
-          console.log(file)
-          const formData = new FormData()
+          let formData = new FormData()
           formData.append('document', file, file.name)
-          this.documentService.uploadDocument(formData).subscribe(result => {
-            this.toastService.showToast(Toast.make("Information", "The document has been uploaded and will be processed by the consumer shortly."))
+
+          this.documentService.uploadDocument(formData).subscribe(event => {
+            if (event.type == HttpEventType.UploadProgress) {
+              uploadStatusObject.loaded = event.loaded
+              uploadStatusObject.total = event.total
+            } else if (event.type == HttpEventType.Response) {
+              this.uploadStatus.splice(this.uploadStatus.indexOf(uploadStatusObject), 1)
+              this.completedFiles += 1
+              this.toastService.showToast(Toast.make("Information", "The document has been uploaded and will be processed by the consumer shortly."))
+            }
+            
           }, error => {
-            this.toastService.showToast(Toast.makeError("An error has occured while uploading the document. Sorry!"))
+            this.uploadStatus.splice(this.uploadStatus.indexOf(uploadStatusObject), 1)
+            this.completedFiles += 1
+            switch (error.status) {
+              case 400: {
+                this.toastService.showToast(Toast.makeError(`There was an error while uploading the document: ${error.error.document}`))
+                break;
+              }
+              default: {
+                this.toastService.showToast(Toast.makeError("An error has occurred while uploading the document. Sorry!"))
+                break;
+              }
+            }
           })
         });
       }

src-ui/src/app/components/dashboard/widgets/welcome-widget/welcome-widget.component.html

@@ -0,0 +1,16 @@
+<app-widget-frame title="First steps">
+
+  <ng-container content>
+    <img src="assets/save-filter.png" class="float-right">
+    <p>Paperless is running! :)</p>
+    <p>You can start uploading documents by dropping them in the file upload box to the right or by dropping them in the configured consumption folder and they'll start showing up in the documents list.
+      After you've added some metadata to your documents, use the filtering mechanisms of paperless to create custom views (such as 'Recently added', 'Tagged TODO') and have them displayed on the dashboard instead of this message.</p>
+    <p>Paperless offers some more features that try to make your life easier, such as:</p>
+    <ul>
+      <li>Once you've got a couple documents in paperless and added metadata to them, paperless can assign that metadata to new documents automatically.</li>
+      <li>You can configure paperless to read your mails and add documents from attached files.</li>
+    </ul>
+    <p>Consult the documentation on how to use these features. The section on basic usage also has some information on how to use paperless in general.</p>
+  </ng-container>
+
+</app-widget-frame>

src-ui/src/app/components/dashboard/widgets/welcome-widget/welcome-widget.component.spec.ts

@@ -0,0 +1,25 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing';
+
+import { WelcomeWidgetComponent } from './welcome-widget.component';
+
+describe('WelcomeWidgetComponent', () => {
+  let component: WelcomeWidgetComponent;
+  let fixture: ComponentFixture<WelcomeWidgetComponent>;
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [ WelcomeWidgetComponent ]
+    })
+    .compileComponents();
+  });
+
+  beforeEach(() => {
+    fixture = TestBed.createComponent(WelcomeWidgetComponent);
+    component = fixture.componentInstance;
+    fixture.detectChanges();
+  });
+
+  it('should create', () => {
+    expect(component).toBeTruthy();
+  });
+});

src-ui/src/app/components/dashboard/widgets/welcome-widget/welcome-widget.component.ts

@@ -0,0 +1,15 @@
+import { Component, OnInit } from '@angular/core';
+
+@Component({
+  selector: 'app-welcome-widget',
+  templateUrl: './welcome-widget.component.html',
+  styleUrls: ['./welcome-widget.component.scss']
+})
+export class WelcomeWidgetComponent implements OnInit {
+
+  constructor() { }
+
+  ngOnInit(): void {
+  }
+
+}

src-ui/src/app/components/dashboard/widgets/widget-frame/widget-frame.component.html

@@ -1,8 +1,12 @@
-<div class="card mb-3 shadow">
+<div class="card mb-3 shadow-sm">
   <div class="card-header">
-    <h5 class="card-title mb-0">{{title}}</h5>
+    <div class="d-flex justify-content-between align-items-center">
+      <h5 class="card-title mb-0">{{title}}</h5>
+      <ng-content select ="[header-buttons]"></ng-content>
+    </div>
+    
   </div>
   <div class="card-body text-dark">
-    <ng-content></ng-content>
+    <ng-content select ="[content]"></ng-content>
   </div>
 </div>

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -5,12 +5,26 @@
         </svg>
         <span class="d-none d-lg-inline"> Delete</span>
     </button>
-    <a [href]="downloadUrl" class="btn btn-sm btn-outline-primary mr-2">
-        <svg class="buttonicon" fill="currentColor">
-            <use xlink:href="assets/bootstrap-icons.svg#download" />
-        </svg>
-        <span class="d-none d-lg-inline"> Download</span>
-    </a>
+
+    <div class="btn-group mr-2">
+
+        <a [href]="downloadUrl" class="btn btn-sm btn-outline-primary">
+            <svg class="buttonicon" fill="currentColor">
+                <use xlink:href="assets/bootstrap-icons.svg#download" />
+            </svg>
+            <span class="d-none d-lg-inline"> Download</span>
+        </a>
+
+        <div class="btn-group" ngbDropdown role="group" *ngIf="metadata?.has_archive_version">
+            <button class="btn btn-sm btn-outline-primary dropdown-toggle-split" ngbDropdownToggle></button>
+            <div class="dropdown-menu shadow" ngbDropdownMenu>
+                <a ngbDropdownItem [href]="downloadOriginalUrl">Download original</a>
+            </div>
+        </div>
+
+    </div>
+
+
     <button type="button" class="btn btn-sm btn-outline-primary" (click)="close()">
         <svg class="buttonicon" fill="currentColor">
             <use xlink:href="assets/bootstrap-icons.svg#x" />
@@ -21,41 +35,100 @@
 
 
 <div class="row">
-    <div class="col-xl">
+    <div class="col mb-4">
+
         <form [formGroup]='documentForm' (ngSubmit)="save()">
 
-            <app-input-text title="Title" formControlName="title"></app-input-text>
+            <ul ngbNav #nav="ngbNav" class="nav-tabs">
+                <li [ngbNavItem]="1">
+                    <a ngbNavLink>Details</a>
+                    <ng-template ngbNavContent>
 
-            <div class="form-group">
-                <label for="archive_serial_number">Archive Serial Number</label>
-                <input type="number" class="form-control" id="archive_serial_number"
-                    formControlName='archive_serial_number'>
-            </div>
+                        <app-input-text title="Title" formControlName="title"></app-input-text>
+                        <div class="form-group">
+                            <label for="archive_serial_number">Archive Serial Number</label>
+                            <input type="number" class="form-control" id="archive_serial_number"
+                                formControlName='archive_serial_number'>
+                        </div>
+                        <app-input-date-time titleDate="Date created" formControlName="created"></app-input-date-time>
+                        <app-input-select [items]="correspondents" title="Correspondent" formControlName="correspondent"
+                            allowNull="true" (createNew)="createCorrespondent()"></app-input-select>
+                        <app-input-select [items]="documentTypes" title="Document type" formControlName="document_type"
+                            allowNull="true" (createNew)="createDocumentType()"></app-input-select>
+                        <app-input-tags formControlName="tags" title="Tags"></app-input-tags>
 
-            <app-input-date-time title="Date created" titleTime="Time created" formControlName="created"></app-input-date-time>
+                    </ng-template>
+                </li>
 
-            <div class="form-group">
-                <label for="content">Content</label>
-                <textarea class="form-control" id="content" rows="5" formControlName='content'></textarea>
-            </div>
+                <li [ngbNavItem]="2">
+                    <a ngbNavLink>Content</a>
+                    <ng-template ngbNavContent>
+                        <div class="form-group">
+                            <textarea class="form-control" id="content" rows="20" formControlName='content'></textarea>
+                        </div>
+                    </ng-template>
+                </li>
 
-            <app-input-select [items]="correspondents" title="Correspondent" formControlName="correspondent_id" allowNull="true" (createNew)="createCorrespondent()"></app-input-select>
+                <li [ngbNavItem]="3">
+                    <a ngbNavLink>Metadata</a>
+                    <ng-template ngbNavContent>
 
-            <app-input-select [items]="documentTypes" title="Document type" formControlName="document_type_id" allowNull="true" (createNew)="createDocumentType()"></app-input-select>
+                        <table class="table table-borderless">
+                            <tbody>
+                                <tr>
+                                    <td>Date modified</td>
+                                    <td>{{document.modified | date:'medium'}}</td>
+                                </tr>
+                                <tr>
+                                    <td>Date added</td>
+                                    <td>{{document.added | date:'medium'}}</td>
+                                </tr>
+                                <tr>
+                                    <td>Media filename</td>
+                                    <td>{{metadata?.media_filename}}</td>
+                                </tr>
+                                <tr>
+                                    <td>Original MD5 Checksum</td>
+                                    <td>{{metadata?.original_checksum}}</td>
+                                </tr>
+                                <tr>
+                                    <td>Original file size</td>
+                                    <td>{{metadata?.original_size | fileSize}}</td>
+                                </tr>
+                                <tr>
+                                    <td>Original mime type</td>
+                                    <td>{{metadata?.original_mime_type}}</td>
+                                </tr>
+                                <tr *ngIf="metadata?.has_archive_version">
+                                    <td>Archive MD5 Checksum</td>
+                                    <td>{{metadata?.archive_checksum}}</td>
+                                </tr>
+                                <tr *ngIf="metadata?.has_archive_version">
+                                    <td>Archive file size</td>
+                                    <td>{{metadata?.archive_size | fileSize}}</td>
+                                </tr>
+                            </tbody>
+                        </table>
 
-            <app-input-tags formControlName="tags_id" title="Tags"></app-input-tags>
+                        <app-metadata-collapse title="Original document metadata" [metadata]="metadata.original_metadata" *ngIf="metadata?.original_metadata?.length > 0"></app-metadata-collapse>
+                        <app-metadata-collapse title="Archived document metadata" [metadata]="metadata.archive_metadata" *ngIf="metadata?.archive_metadata?.length > 0"></app-metadata-collapse>
+
+                    </ng-template>
+                </li>
+            </ul>
+
+            <div [ngbNavOutlet]="nav" class="mt-2"></div>
 
             <button type="button" class="btn btn-outline-secondary" (click)="discard()">Discard</button>&nbsp;
-            <button type="button" class="btn btn-outline-primary" (click)="saveEditNext()" *ngIf="hasNext()">Save & edit next</button>&nbsp;
+            <button type="button" class="btn btn-outline-primary" (click)="saveEditNext()" *ngIf="hasNext()">Save & edit
+                next</button>&nbsp;
             <button type="submit" class="btn btn-primary">Save</button>&nbsp;
         </form>
     </div>
 
-    <div class="col-xl">
-        <object [data]="previewUrl | safe" type="application/pdf" width="100%" height="100%">
-            <p>Your browser does not support PDFs.
-                <a href="previewUrl">Download the PDF</a>.</p>
-        </object>
-
+    <div class="col-md-6 col-xl-8 mb-3">
+      <div class="pdf-viewer-container" *ngIf="getContentType() == 'application/pdf'">
+        <pdf-viewer [src]="previewUrl" [original-size]="false" [show-borders]="true"></pdf-viewer>
+      </div>
     </div>
 </div>

src-ui/src/app/components/document-detail/document-detail.component.scss

@@ -0,0 +1,6 @@
+.pdf-viewer-container {
+  height: calc(100vh - 160px);
+  top: 70px;
+  position: sticky;
+  background-color: gray;
+}

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -1,22 +1,20 @@
-import { DatePipe, formatDate } from '@angular/common';
 import { Component, OnInit } from '@angular/core';
 import { FormControl, FormGroup } from '@angular/forms';
 import { ActivatedRoute, Router } from '@angular/router';
 import { NgbModal } from '@ng-bootstrap/ng-bootstrap';
 import { PaperlessCorrespondent } from 'src/app/data/paperless-correspondent';
 import { PaperlessDocument } from 'src/app/data/paperless-document';
+import { PaperlessDocumentMetadata } from 'src/app/data/paperless-document-metadata';
 import { PaperlessDocumentType } from 'src/app/data/paperless-document-type';
-import { TAG_COLOURS, PaperlessTag } from 'src/app/data/paperless-tag';
+import { DocumentTitlePipe } from 'src/app/pipes/document-title.pipe';
 import { DocumentListViewService } from 'src/app/services/document-list-view.service';
 import { OpenDocumentsService } from 'src/app/services/open-documents.service';
 import { CorrespondentService } from 'src/app/services/rest/correspondent.service';
 import { DocumentTypeService } from 'src/app/services/rest/document-type.service';
 import { DocumentService } from 'src/app/services/rest/document.service';
-import { TagService } from 'src/app/services/rest/tag.service';
-import { DeleteDialogComponent } from '../common/delete-dialog/delete-dialog.component';
+import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component';
 import { CorrespondentEditDialogComponent } from '../manage/correspondent-list/correspondent-edit-dialog/correspondent-edit-dialog.component';
 import { DocumentTypeEditDialogComponent } from '../manage/document-type-list/document-type-edit-dialog/document-type-edit-dialog.component';
-import { TagEditDialogComponent } from '../manage/tag-list/tag-edit-dialog/tag-edit-dialog.component';
 
 @Component({
   selector: 'app-document-detail',
@@ -25,11 +23,16 @@ import { TagEditDialogComponent } from '../manage/tag-list/tag-edit-dialog/tag-e
 })
 export class DocumentDetailComponent implements OnInit {
 
+  public expandOriginalMetadata = false;
+  public expandArchivedMetadata = false;
+
   documentId: number
   document: PaperlessDocument
+  metadata: PaperlessDocumentMetadata
   title: string
   previewUrl: string
   downloadUrl: string
+  downloadOriginalUrl: string
 
   correspondents: PaperlessCorrespondent[]
   documentTypes: PaperlessDocumentType[]
@@ -38,10 +41,10 @@ export class DocumentDetailComponent implements OnInit {
     title: new FormControl(''),
     content: new FormControl(''),
     created: new FormControl(),
-    correspondent_id: new FormControl(),
-    document_type_id: new FormControl(),
+    correspondent: new FormControl(),
+    document_type: new FormControl(),
     archive_serial_number: new FormControl(),
-    tags_id: new FormControl([])
+    tags: new FormControl([])
   })
 
   constructor(
@@ -52,7 +55,12 @@ export class DocumentDetailComponent implements OnInit {
     private router: Router,
     private modalService: NgbModal,
     private openDocumentService: OpenDocumentsService,
-    private documentListViewService: DocumentListViewService) { }
+    private documentListViewService: DocumentListViewService,
+    private documentTitlePipe: DocumentTitlePipe) { }
+
+  getContentType() {
+    return this.metadata?.has_archive_version ? 'application/pdf' : this.metadata?.original_mime_type
+  }
 
   ngOnInit(): void {
     this.documentForm.valueChanges.subscribe(wow => {
@@ -66,6 +74,7 @@ export class DocumentDetailComponent implements OnInit {
       this.documentId = +paramMap.get('id')
       this.previewUrl = this.documentsService.getPreviewUrl(this.documentId)
       this.downloadUrl = this.documentsService.getDownloadUrl(this.documentId)
+      this.downloadOriginalUrl = this.documentsService.getDownloadUrl(this.documentId, true)
       if (this.openDocumentService.getOpenDocument(this.documentId)) {
         this.updateComponent(this.openDocumentService.getOpenDocument(this.documentId))
       } else {
@@ -80,7 +89,10 @@ export class DocumentDetailComponent implements OnInit {
 
   updateComponent(doc: PaperlessDocument) {
     this.document = doc
-    this.title = doc.title
+    this.documentsService.getMetadata(doc.id).subscribe(result => {
+      this.metadata = result
+    })
+    this.title = this.documentTitlePipe.transform(doc.title)
     this.documentForm.patchValue(doc)
   }
 
@@ -90,7 +102,7 @@ export class DocumentDetailComponent implements OnInit {
     modal.componentInstance.success.subscribe(newDocumentType => {
       this.documentTypeService.listAll().subscribe(documentTypes => {
         this.documentTypes = documentTypes.results
-        this.documentForm.get('document_type_id').setValue(newDocumentType.id)
+        this.documentForm.get('document_type').setValue(newDocumentType.id)
       })
     })
   }
@@ -101,7 +113,7 @@ export class DocumentDetailComponent implements OnInit {
     modal.componentInstance.success.subscribe(newCorrespondent => {
       this.correspondentService.listAll().subscribe(correspondents => {
         this.correspondents = correspondents.results
-        this.documentForm.get('correspondent_id').setValue(newCorrespondent.id)
+        this.documentForm.get('correspondent').setValue(newCorrespondent.id)
       })
     })
   }
@@ -133,18 +145,21 @@ export class DocumentDetailComponent implements OnInit {
 
   close() {
     this.openDocumentService.closeDocument(this.document)
-    if (this.documentListViewService.viewId) {
-      this.router.navigate(['view', this.documentListViewService.viewId])
+    if (this.documentListViewService.savedViewId) {
+      this.router.navigate(['view', this.documentListViewService.savedViewId])
     } else {
       this.router.navigate(['documents'])
     }
   }
 
   delete() {
-    let modal = this.modalService.open(DeleteDialogComponent, {backdrop: 'static'})
-    modal.componentInstance.message = `Do you really want to delete document '${this.document.title}'?`
-    modal.componentInstance.message2 = `The files for this document will be deleted permanently. This operation cannot be undone.`
-    modal.componentInstance.deleteClicked.subscribe(() => {
+    let modal = this.modalService.open(ConfirmDialogComponent, {backdrop: 'static'})
+    modal.componentInstance.title = "Confirm delete"
+    modal.componentInstance.messageBold = `Do you really want to delete document '${this.document.title}'?`
+    modal.componentInstance.message = `The files for this document will be deleted permanently. This operation cannot be undone.`
+    modal.componentInstance.btnClass = "btn-danger"
+    modal.componentInstance.btnCaption = "Delete document"
+    modal.componentInstance.confirmClicked.subscribe(() => {
       this.documentsService.delete(this.document).subscribe(() => {
         modal.close()  
         this.close()

src-ui/src/app/components/document-detail/metadata-collapse/metadata-collapse.component.html

@@ -0,0 +1,23 @@
+<h6>
+  <button type="button" class="btn btn-outline-secondary btn-sm mr-2"
+      (click)="expand = !expand">
+      <svg class="buttonicon" fill="currentColor" *ngIf="!expand">
+          <use xlink:href="assets/bootstrap-icons.svg#caret-down" />
+      </svg>
+      <svg class="buttonicon" fill="currentColor" *ngIf="expand">
+          <use xlink:href="assets/bootstrap-icons.svg#caret-up" />
+      </svg>
+  </button>
+  {{title}}
+</h6>
+
+<div #collapse="ngbCollapse" [(ngbCollapse)]="!expand">
+  <table class="table table-borderless">
+      <tbody>
+          <tr *ngFor="let m of metadata">
+              <td>{{m.prefix}}:{{m.key}}</td>
+              <td>{{m.value}}</td>
+          </tr>
+      </tbody>
+  </table>
+</div>

src-ui/src/app/components/document-detail/metadata-collapse/metadata-collapse.component.spec.ts

@@ -1,20 +1,20 @@
 import { ComponentFixture, TestBed } from '@angular/core/testing';
 
-import { ResultHightlightComponent } from './result-hightlight.component';
+import { MetadataCollapseComponent } from './metadata-collapse.component';
 
-describe('ResultHightlightComponent', () => {
-  let component: ResultHightlightComponent;
-  let fixture: ComponentFixture<ResultHightlightComponent>;
+describe('MetadataCollapseComponent', () => {
+  let component: MetadataCollapseComponent;
+  let fixture: ComponentFixture<MetadataCollapseComponent>;
 
   beforeEach(async () => {
     await TestBed.configureTestingModule({
-      declarations: [ ResultHightlightComponent ]
+      declarations: [ MetadataCollapseComponent ]
     })
     .compileComponents();
   });
 
   beforeEach(() => {
-    fixture = TestBed.createComponent(ResultHightlightComponent);
+    fixture = TestBed.createComponent(MetadataCollapseComponent);
     component = fixture.componentInstance;
     fixture.detectChanges();
   });

src-ui/src/app/components/document-detail/metadata-collapse/metadata-collapse.component.ts

@@ -0,0 +1,23 @@
+import { Component, Input, OnInit } from '@angular/core';
+
+@Component({
+  selector: 'app-metadata-collapse',
+  templateUrl: './metadata-collapse.component.html',
+  styleUrls: ['./metadata-collapse.component.scss']
+})
+export class MetadataCollapseComponent implements OnInit {
+
+  constructor() { }
+
+  expand = false
+
+  @Input()
+  metadata
+
+  @Input()
+  title = "Metadata"
+
+  ngOnInit(): void {
+  }
+
+}

src-ui/src/app/components/document-list/document-card-large/document-card-large.component.html

@@ -7,11 +7,18 @@
       <div class="card-body">
 
         <div class="d-flex justify-content-between align-items-center">
-          <h5 class="card-title">{{document.correspondent ? document.correspondent.name + ': ' : ''}}{{document.title}}<app-tag [tag]="t" *ngFor="let t of document.tags" class="ml-1"></app-tag></h5>
+          <h5 class="card-title">
+            <ng-container *ngIf="document.correspondent">
+              <a *ngIf="clickCorrespondent.observers.length ; else nolink" [routerLink]="" title="Filter by correspondent" (click)="clickCorrespondent.emit(document.correspondent)" class="font-weight-bold">{{(document.correspondent$ | async)?.name}}</a>
+              <ng-template #nolink>{{(document.correspondent$ | async)?.name}}</ng-template>:
+            </ng-container>
+            {{document.title | documentTitle}}
+            <app-tag [tag]="t" linkTitle="Filter by tag" *ngFor="let t of document.tags$ | async" class="ml-1" (click)="clickTag.emit(t.id)" [clickable]="clickTag.observers.length"></app-tag>
+          </h5>
           <h5 class="card-title" *ngIf="document.archive_serial_number">#{{document.archive_serial_number}}</h5>
         </div>
         <p class="card-text">
-          <app-result-hightlight *ngIf="getDetailsAsHighlight()" class="result-content" [highlights]="getDetailsAsHighlight()"></app-result-hightlight>
+          <app-result-highlight *ngIf="getDetailsAsHighlight()" class="result-content" [highlights]="getDetailsAsHighlight()"></app-result-highlight>
           <span *ngIf="getDetailsAsString()" class="result-content">{{getDetailsAsString()}}</span>
         </p>
 
@@ -24,6 +31,13 @@
               </svg>
               Edit
             </a>
+            <a type="button" class="btn btn-sm btn-outline-secondary" [href]="getPreviewUrl()">
+              <svg width="1em" height="1em" viewBox="0 0 16 16" class="bi bi-search" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+                <path fill-rule="evenodd" d="M10.442 10.442a1 1 0 0 1 1.415 0l3.85 3.85a1 1 0 0 1-1.414 1.415l-3.85-3.85a1 1 0 0 1 0-1.415z"/>
+                <path fill-rule="evenodd" d="M6.5 12a5.5 5.5 0 1 0 0-11 5.5 5.5 0 0 0 0 11zM13 6.5a6.5 6.5 0 1 1-13 0 6.5 6.5 0 0 1 13 0z"/>
+              </svg>
+              View
+            </a>
             <a type="button" class="btn btn-sm btn-outline-secondary" [href]="getDownloadUrl()">
               <svg width="1em" height="1em" viewBox="0 0 16 16" class="bi bi-download" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
                 <path fill-rule="evenodd" d="M.5 9.9a.5.5 0 0 1 .5.5v2.5a1 1 0 0 0 1 1h12a1 1 0 0 0 1-1v-2.5a.5.5 0 0 1 1 0v2.5a2 2 0 0 1-2 2H2a2 2 0 0 1-2-2v-2.5a.5.5 0 0 1 .5-.5z"/>
@@ -38,4 +52,4 @@
       </div>
     </div>
   </div>
-</div>
+</div>

src-ui/src/app/components/document-list/document-card-large/document-card-large.component.scss

@@ -1,5 +1,6 @@
 .result-content {
   color: darkgray;
+  overflow-wrap: anywhere;
 }
 
 .doc-img {

src-ui/src/app/components/document-list/document-card-large/document-card-large.component.ts

@@ -1,4 +1,4 @@
-import { Component, Input, OnInit } from '@angular/core';
+import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
 import { DomSanitizer } from '@angular/platform-browser';
 import { PaperlessDocument } from 'src/app/data/paperless-document';
 import { DocumentService } from 'src/app/services/rest/document.service';
@@ -18,6 +18,12 @@ export class DocumentCardLargeComponent implements OnInit {
   @Input()
   details: any
 
+  @Output()
+  clickTag = new EventEmitter<number>()
+
+  @Output()
+  clickCorrespondent = new EventEmitter<number>()
+
   ngOnInit(): void {
   }
 
@@ -41,4 +47,8 @@ export class DocumentCardLargeComponent implements OnInit {
   getDownloadUrl() {
     return this.documentService.getDownloadUrl(this.document.id)
   }
+
+  getPreviewUrl() {
+    return this.documentService.getPreviewUrl(this.document.id)
+  }
 }

src-ui/src/app/components/document-list/document-card-small/document-card-small.component.html

@@ -1,27 +1,41 @@
 <div class="col p-2 h-100" style="width: 16rem;">
   <div class="card h-100 shadow-sm">
-    <div class=" border-bottom doc-img pr-1" [ngStyle]="{'background-image': 'url(' + getThumbUrl() + ')'}">
-      <div class="row" *ngFor="let t of document.tags">
-        <app-tag [tag]="t" class="col text-right"></app-tag>
+    <div class="border-bottom">
+      <img class="card-img doc-img" [src]="getThumbUrl()">
+      <div style="top: 0; right: 0; font-size: large" class="text-right position-absolute mr-1">
+        <div *ngFor="let t of getTagsLimited$() | async">
+          <app-tag [tag]="t" (click)="clickTag.emit(t.id)" [clickable]="true" linkTitle="Filter by tag"></app-tag>
+        </div>
+        <div *ngIf="moreTags">
+          <span class="badge badge-secondary">+ {{moreTags}}</span>
+        </div>
       </div>
     </div>
 
-    
     <div class="card-body p-2">
       <p class="card-text">
-        <span class="font-weight-bold">{{document.correspondent? document.correspondent.name + ': ' : ''}}</span> {{document.title}}
+        <ng-container *ngIf="document.correspondent">
+          <a [routerLink]="" title="Filter by correspondent" (click)="clickCorrespondent.emit(document.correspondent)" class="font-weight-bold">{{(document.correspondent$ | async)?.name}}</a>:
+        </ng-container>
+        {{document.title | documentTitle}}
       </p>
     </div>
     <div class="card-footer">
 
       <div class="d-flex justify-content-between align-items-center ml-n2">
         <div class="btn-group">
-          <a routerLink="/documents/{{document.id}}" class="btn btn-sm btn-outline-secondary">
+          <a routerLink="/documents/{{document.id}}" class="btn btn-sm btn-outline-secondary" title="Edit">
             <svg width="1em" height="1em" viewBox="0 0 16 16" class="bi bi-pencil" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
               <path fill-rule="evenodd" d="M12.146.146a.5.5 0 0 1 .708 0l3 3a.5.5 0 0 1 0 .708l-10 10a.5.5 0 0 1-.168.11l-5 2a.5.5 0 0 1-.65-.65l2-5a.5.5 0 0 1 .11-.168l10-10zM11.207 2.5L13.5 4.793 14.793 3.5 12.5 1.207 11.207 2.5zm1.586 3L10.5 3.207 4 9.707V10h.5a.5.5 0 0 1 .5.5v.5h.5a.5.5 0 0 1 .5.5v.5h.293l6.5-6.5zm-9.761 5.175l-.106.106-1.528 3.821 3.821-1.528.106-.106A.5.5 0 0 1 5 12.5V12h-.5a.5.5 0 0 1-.5-.5V11h-.5a.5.5 0 0 1-.468-.325z"/>
             </svg>
           </a>
-          <a [href]="getDownloadUrl()" class="btn btn-sm btn-outline-secondary">
+          <a [href]="getPreviewUrl()" class="btn btn-sm btn-outline-secondary" title="View in browser">
+            <svg width="1em" height="1em" viewBox="0 0 16 16" class="bi bi-search" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+              <path fill-rule="evenodd" d="M10.442 10.442a1 1 0 0 1 1.415 0l3.85 3.85a1 1 0 0 1-1.414 1.415l-3.85-3.85a1 1 0 0 1 0-1.415z"/>
+              <path fill-rule="evenodd" d="M6.5 12a5.5 5.5 0 1 0 0-11 5.5 5.5 0 0 0 0 11zM13 6.5a6.5 6.5 0 1 1-13 0 6.5 6.5 0 0 1 13 0z"/>
+            </svg>
+          </a>
+          <a [href]="getDownloadUrl()" class="btn btn-sm btn-outline-secondary" title="Download">
             <svg width="1em" height="1em" viewBox="0 0 16 16" class="bi bi-download" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
               <path fill-rule="evenodd" d="M.5 9.9a.5.5 0 0 1 .5.5v2.5a1 1 0 0 0 1 1h12a1 1 0 0 0 1-1v-2.5a.5.5 0 0 1 1 0v2.5a2 2 0 0 1-2 2H2a2 2 0 0 1-2-2v-2.5a.5.5 0 0 1 .5-.5z"/>
               <path fill-rule="evenodd" d="M7.646 11.854a.5.5 0 0 0 .708 0l3-3a.5.5 0 0 0-.708-.708L8.5 10.293V1.5a.5.5 0 0 0-1 0v8.793L5.354 8.146a.5.5 0 1 0-.708.708l3 3z"/>
@@ -30,7 +44,7 @@
         </div>
         <small class="text-muted">{{document.created | date}}</small>
       </div>
-      
+
     </div>
-  </div>  
-</div>
+  </div>
+</div>