mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-08-05 18:58:34 -05:00
Compare commits
92 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
c6a51a1cdc | ||
|
|
4b20d5d4b9 | ||
|
|
cccd183c31 | ||
|
|
1baa203ef2 | ||
|
|
c3ce05e1cd | ||
|
|
7659dde16c | ||
|
|
872d657361 | ||
|
|
ea58c66fd4 | ||
|
|
bcd9220021 | ||
|
|
766109ae4e | ||
|
|
b347e3347d | ||
|
|
7257cece30 | ||
|
|
5b9f38d398 | ||
|
|
b31d4779bf | ||
|
|
60618381f8 | ||
|
|
779ea6a015 | ||
|
|
94ede7389d | ||
|
|
03beca7838 | ||
|
|
fb1dcb6e08 | ||
|
|
a298cbd4ce | ||
|
|
f1a1e7f1a4 | ||
|
|
8371c2399f | ||
|
|
909586bf25 | ||
|
|
8d003a6a85 | ||
|
|
0209b71404 | ||
|
|
0dc3644cc1 | ||
|
|
fb1a2ee577 | ||
|
|
7c589f71a4 | ||
|
|
25a6aa909b | ||
|
|
ef0d37985b | ||
|
|
898931cc03 | ||
|
|
17803e7936 | ||
|
|
e72735c4f0 | ||
|
|
46a5bc00d7 | ||
|
|
d46ee11143 | ||
|
|
d2534a73e5 | ||
|
|
11adc94e5e | ||
|
|
04bf5fc094 | ||
|
|
d26f940a91 | ||
|
|
13725ef8ee | ||
|
|
6f0ca432c4 | ||
|
|
dd8746bac7 | ||
|
|
8eeded95c4 | ||
|
|
131e1c9dd8 | ||
|
|
a6b4fc7e81 | ||
|
|
cea880f245 | ||
|
|
82bc0e3368 | ||
|
|
70bd05450a | ||
|
|
c765ef5eeb | ||
|
|
30134034e2 | ||
|
|
8a1a736340 | ||
|
|
68652c8c37 | ||
|
|
c091eba26e | ||
|
|
ca315ba76c | ||
|
|
350da81081 | ||
|
|
4129002086 | ||
|
|
781a1dae71 | ||
|
|
01fed4f49d | ||
|
|
d7ab69fed9 | ||
|
|
dfa5ea423f | ||
|
|
a698a1b66b | ||
|
|
a5129018d2 | ||
|
|
e3974c68ba | ||
|
|
d72604eb86 | ||
|
|
f0c94cc65f | ||
|
|
f21debe95d | ||
|
|
033ab72475 | ||
|
|
b059602050 | ||
|
|
2775dfb735 | ||
|
|
04384c7037 | ||
|
|
75beb91791 | ||
|
|
b138f4b52b | ||
|
|
d108a69f1b | ||
|
|
bdaea3915e | ||
|
|
9e71b70d4b | ||
|
|
960340a5db | ||
|
|
b3709663f1 | ||
|
|
9f20175cd3 | ||
|
|
adf57b2669 | ||
|
|
f2c32d840e | ||
|
|
ba9d7c8892 | ||
|
|
270b0487ec | ||
|
|
a63880ed19 | ||
|
|
a40737bd0e | ||
|
|
c5b315f518 | ||
|
|
e143a20f50 | ||
|
|
c3a144f2ca | ||
|
|
38bb1f9672 | ||
|
|
22da848be4 | ||
|
|
a53e30e0a5 | ||
|
|
7a2bd58ef8 | ||
|
|
8f6231bd34 |
@@ -18,9 +18,6 @@ max_line_length = off
|
||||
indent_size = 4
|
||||
indent_style = space
|
||||
|
||||
[*.yml]
|
||||
indent_style = space
|
||||
|
||||
# Tests don't get a line width restriction. It's still a good idea to follow
|
||||
# the 79 character rule, but in the interests of clarity, tests often need to
|
||||
# violate it.
|
||||
|
||||
6
.gitignore
vendored
6
.gitignore
vendored
@@ -66,7 +66,6 @@ media/overrides.js
|
||||
|
||||
# Sqlite database
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# PyCharm
|
||||
.idea
|
||||
@@ -82,4 +81,7 @@ scripts/import-for-development
|
||||
scripts/nuke
|
||||
|
||||
# Static files collected by the collectstatic command
|
||||
./static/
|
||||
static/
|
||||
|
||||
# Classification Models
|
||||
models/
|
||||
|
||||
17
.travis.yml
17
.travis.yml
@@ -2,22 +2,19 @@ language: python
|
||||
|
||||
before_install:
|
||||
- sudo apt-get update -qq
|
||||
- sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr
|
||||
- sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr tesseract-ocr-eng tesseract-ocr-cat tesseract-ocr-deu
|
||||
|
||||
sudo: false
|
||||
|
||||
matrix:
|
||||
include:
|
||||
- python: "3.4"
|
||||
- python: "3.5"
|
||||
- python: "3.6"
|
||||
- python: "3.7-dev"
|
||||
- python: 3.4
|
||||
- python: 3.5
|
||||
- python: 3.6
|
||||
|
||||
install:
|
||||
- pip install --upgrade pip pipenv sphinx
|
||||
- pipenv lock -r > requirements.txt
|
||||
- pip install -r requirements.txt
|
||||
|
||||
- pip install --requirement requirements.txt
|
||||
- pip install sphinx
|
||||
script:
|
||||
- cd src/
|
||||
- pytest --cov
|
||||
@@ -25,4 +22,4 @@ script:
|
||||
- sphinx-build -b html ../docs ../docs/_build -W
|
||||
|
||||
after_success:
|
||||
- coveralls
|
||||
- coveralls
|
||||
|
||||
@@ -4,8 +4,8 @@ LABEL maintainer="The Paperless Project https://github.com/danielquinn/paperless
|
||||
contributors="Guy Addadi <addadi@gmail.com>, Pit Kleyersburg <pitkley@googlemail.com>, \
|
||||
Sven Fischer <git-dev@linux4tw.de>"
|
||||
|
||||
# Copy Pipfiles file and init script
|
||||
COPY Pipfile* /usr/src/paperless/
|
||||
# Copy requirements file and init script
|
||||
COPY requirements.txt /usr/src/paperless/
|
||||
COPY scripts/docker-entrypoint.sh /sbin/docker-entrypoint.sh
|
||||
|
||||
# Set export and consumption directories
|
||||
@@ -21,8 +21,7 @@ RUN apk update --no-cache && apk add python3 gnupg libmagic libpq bash shadow cu
|
||||
python3 -m ensurepip && \
|
||||
rm -r /usr/lib/python*/ensurepip && \
|
||||
cd /usr/src/paperless && \
|
||||
pip3 install --upgrade pip pipenv && \
|
||||
pipenv install --system --deploy && \
|
||||
pip3 install --no-cache-dir -r requirements.txt && \
|
||||
# Remove build dependencies
|
||||
apk del .build-dependencies && \
|
||||
# Create the consumption directory
|
||||
|
||||
2
Pipfile
2
Pipfile
@@ -34,8 +34,6 @@ pytest-django = "*"
|
||||
pytest-sugar = "*"
|
||||
pytest-env = "*"
|
||||
pytest-xdist = "*"
|
||||
psycopg2 = "*"
|
||||
djangoql = "*"
|
||||
|
||||
[dev-packages]
|
||||
ipython = "*"
|
||||
|
||||
556
Pipfile.lock
generated
556
Pipfile.lock
generated
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"_meta": {
|
||||
"hash": {
|
||||
"sha256": "971e0c975821925652865e34eed1c668bc6f52bb8217b776f35e87a66c936e1b"
|
||||
"sha256": "3782f7e6b5461c39c8fd0d0048a4622418f247439113bd3cdc91712fd47036f6"
|
||||
},
|
||||
"pipfile-spec": 6,
|
||||
"requires": {},
|
||||
@@ -49,12 +49,19 @@
|
||||
],
|
||||
"version": "==2.6.0"
|
||||
},
|
||||
"backcall": {
|
||||
"hashes": [
|
||||
"sha256:38ecd85be2c1e78f77fd91700c76e14667dc21e2713b63876c0eb901196e01e4",
|
||||
"sha256:bbbf4b1e5cd2bdb08f915895b51081c041bac22394fdfcfdfbe9f14b77c08bf2"
|
||||
],
|
||||
"version": "==0.1.0"
|
||||
},
|
||||
"certifi": {
|
||||
"hashes": [
|
||||
"sha256:47f9c83ef4c0c621eaef743f133f09fa8a74a9b75f037e8624f83bd1b6626cb7",
|
||||
"sha256:993f830721089fef441cdfeb4b2c8c9df86f0c63239f06bd025a76a7daddb033"
|
||||
"sha256:339dc09518b07e2fa7eda5450740925974815557727d6bd35d319c1524a04a4c",
|
||||
"sha256:6d58c986d22b038c8c0df30d639f23a3e6d172a05c3583e766f4c0b785c0986a"
|
||||
],
|
||||
"version": "==2018.11.29"
|
||||
"version": "==2018.10.15"
|
||||
},
|
||||
"chardet": {
|
||||
"hashes": [
|
||||
@@ -65,39 +72,41 @@
|
||||
},
|
||||
"coverage": {
|
||||
"hashes": [
|
||||
"sha256:09e47c529ff77bf042ecfe858fb55c3e3eb97aac2c87f0349ab5a7efd6b3939f",
|
||||
"sha256:0a1f9b0eb3aa15c990c328535655847b3420231af299386cfe5efc98f9c250fe",
|
||||
"sha256:0cc941b37b8c2ececfed341444a456912e740ecf515d560de58b9a76562d966d",
|
||||
"sha256:10e8af18d1315de936d67775d3a814cc81d0747a1a0312d84e27ae5610e313b0",
|
||||
"sha256:1b4276550b86caa60606bd3572b52769860a81a70754a54acc8ba789ce74d607",
|
||||
"sha256:1e8a2627c48266c7b813975335cfdea58c706fe36f607c97d9392e61502dc79d",
|
||||
"sha256:2b224052bfd801beb7478b03e8a66f3f25ea56ea488922e98903914ac9ac930b",
|
||||
"sha256:447c450a093766744ab53bf1e7063ec82866f27bcb4f4c907da25ad293bba7e3",
|
||||
"sha256:46101fc20c6f6568561cdd15a54018bb42980954b79aa46da8ae6f008066a30e",
|
||||
"sha256:4710dc676bb4b779c4361b54eb308bc84d64a2fa3d78e5f7228921eccce5d815",
|
||||
"sha256:510986f9a280cd05189b42eee2b69fecdf5bf9651d4cd315ea21d24a964a3c36",
|
||||
"sha256:5535dda5739257effef56e49a1c51c71f1d37a6e5607bb25a5eee507c59580d1",
|
||||
"sha256:5a7524042014642b39b1fcae85fb37556c200e64ec90824ae9ecf7b667ccfc14",
|
||||
"sha256:5f55028169ef85e1fa8e4b8b1b91c0b3b0fa3297c4fb22990d46ff01d22c2d6c",
|
||||
"sha256:6694d5573e7790a0e8d3d177d7a416ca5f5c150742ee703f3c18df76260de794",
|
||||
"sha256:6831e1ac20ac52634da606b658b0b2712d26984999c9d93f0c6e59fe62ca741b",
|
||||
"sha256:77f0d9fa5e10d03aa4528436e33423bfa3718b86c646615f04616294c935f840",
|
||||
"sha256:828ad813c7cdc2e71dcf141912c685bfe4b548c0e6d9540db6418b807c345ddd",
|
||||
"sha256:85a06c61598b14b015d4df233d249cd5abfa61084ef5b9f64a48e997fd829a82",
|
||||
"sha256:8cb4febad0f0b26c6f62e1628f2053954ad2c555d67660f28dfb1b0496711952",
|
||||
"sha256:a5c58664b23b248b16b96253880b2868fb34358911400a7ba39d7f6399935389",
|
||||
"sha256:aaa0f296e503cda4bc07566f592cd7a28779d433f3a23c48082af425d6d5a78f",
|
||||
"sha256:ab235d9fe64833f12d1334d29b558aacedfbca2356dfb9691f2d0d38a8a7bfb4",
|
||||
"sha256:b3b0c8f660fae65eac74fbf003f3103769b90012ae7a460863010539bb7a80da",
|
||||
"sha256:bab8e6d510d2ea0f1d14f12642e3f35cefa47a9b2e4c7cea1852b52bc9c49647",
|
||||
"sha256:c45297bbdbc8bb79b02cf41417d63352b70bcb76f1bbb1ee7d47b3e89e42f95d",
|
||||
"sha256:d19bca47c8a01b92640c614a9147b081a1974f69168ecd494687c827109e8f42",
|
||||
"sha256:d64b4340a0c488a9e79b66ec9f9d77d02b99b772c8b8afd46c1294c1d39ca478",
|
||||
"sha256:da969da069a82bbb5300b59161d8d7c8d423bc4ccd3b410a9b4d8932aeefc14b",
|
||||
"sha256:ed02c7539705696ecb7dc9d476d861f3904a8d2b7e894bd418994920935d36bb",
|
||||
"sha256:ee5b8abc35b549012e03a7b1e86c09491457dba6c94112a2482b18589cc2bdb9"
|
||||
"sha256:03481e81d558d30d230bc12999e3edffe392d244349a90f4ef9b88425fac74ba",
|
||||
"sha256:0b136648de27201056c1869a6c0d4e23f464750fd9a9ba9750b8336a244429ed",
|
||||
"sha256:0bf8cbbd71adfff0ef1f3a1531e6402d13b7b01ac50a79c97ca15f030dba6306",
|
||||
"sha256:10a46017fef60e16694a30627319f38a2b9b52e90182dddb6e37dcdab0f4bf95",
|
||||
"sha256:198626739a79b09fa0a2f06e083ffd12eb55449b5f8bfdbeed1df4910b2ca640",
|
||||
"sha256:23d341cdd4a0371820eb2b0bd6b88f5003a7438bbedb33688cd33b8eae59affd",
|
||||
"sha256:28b2191e7283f4f3568962e373b47ef7f0392993bb6660d079c62bd50fe9d162",
|
||||
"sha256:2a5b73210bad5279ddb558d9a2bfedc7f4bf6ad7f3c988641d83c40293deaec1",
|
||||
"sha256:2eb564bbf7816a9d68dd3369a510be3327f1c618d2357fa6b1216994c2e3d508",
|
||||
"sha256:337ded681dd2ef9ca04ef5d93cfc87e52e09db2594c296b4a0a3662cb1b41249",
|
||||
"sha256:3a2184c6d797a125dca8367878d3b9a178b6fdd05fdc2d35d758c3006a1cd694",
|
||||
"sha256:3c79a6f7b95751cdebcd9037e4d06f8d5a9b60e4ed0cd231342aa8ad7124882a",
|
||||
"sha256:3d72c20bd105022d29b14a7d628462ebdc61de2f303322c0212a054352f3b287",
|
||||
"sha256:3eb42bf89a6be7deb64116dd1cc4b08171734d721e7a7e57ad64cc4ef29ed2f1",
|
||||
"sha256:4635a184d0bbe537aa185a34193898eee409332a8ccb27eea36f262566585000",
|
||||
"sha256:56e448f051a201c5ebbaa86a5efd0ca90d327204d8b059ab25ad0f35fbfd79f1",
|
||||
"sha256:5a13ea7911ff5e1796b6d5e4fbbf6952381a611209b736d48e675c2756f3f74e",
|
||||
"sha256:69bf008a06b76619d3c3f3b1983f5145c75a305a0fea513aca094cae5c40a8f5",
|
||||
"sha256:6bc583dc18d5979dc0f6cec26a8603129de0304d5ae1f17e57a12834e7235062",
|
||||
"sha256:701cd6093d63e6b8ad7009d8a92425428bc4d6e7ab8d75efbb665c806c1d79ba",
|
||||
"sha256:7608a3dd5d73cb06c531b8925e0ef8d3de31fed2544a7de6c63960a1e73ea4bc",
|
||||
"sha256:76ecd006d1d8f739430ec50cc872889af1f9c1b6b8f48e29941814b09b0fd3cc",
|
||||
"sha256:7aa36d2b844a3e4a4b356708d79fd2c260281a7390d678a10b91ca595ddc9e99",
|
||||
"sha256:7d3f553904b0c5c016d1dad058a7554c7ac4c91a789fca496e7d8347ad040653",
|
||||
"sha256:7e1fe19bd6dce69d9fd159d8e4a80a8f52101380d5d3a4d374b6d3eae0e5de9c",
|
||||
"sha256:8c3cb8c35ec4d9506979b4cf90ee9918bc2e49f84189d9bf5c36c0c1119c6558",
|
||||
"sha256:9d6dd10d49e01571bf6e147d3b505141ffc093a06756c60b053a859cb2128b1f",
|
||||
"sha256:be6cfcd8053d13f5f5eeb284aa8a814220c3da1b0078fa859011c7fffd86dab9",
|
||||
"sha256:c1bb572fab8208c400adaf06a8133ac0712179a334c09224fb11393e920abcdd",
|
||||
"sha256:de4418dadaa1c01d497e539210cb6baa015965526ff5afc078c57ca69160108d",
|
||||
"sha256:e05cb4d9aad6233d67e0541caa7e511fa4047ed7750ec2510d466e806e0255d6",
|
||||
"sha256:f05a636b4564104120111800021a92e43397bc12a5c72fed7036be8556e0029e",
|
||||
"sha256:f3f501f345f24383c0000395b26b726e46758b71393267aeae0bd36f8b3ade80"
|
||||
],
|
||||
"version": "==4.5.2"
|
||||
"version": "==4.5.1"
|
||||
},
|
||||
"coveralls": {
|
||||
"hashes": [
|
||||
@@ -115,13 +124,20 @@
|
||||
"index": "pypi",
|
||||
"version": "==0.7.0"
|
||||
},
|
||||
"decorator": {
|
||||
"hashes": [
|
||||
"sha256:2c51dff8ef3c447388fe5e4453d24a2bf128d3a4c32af3fabef1f01c6851ab82",
|
||||
"sha256:c39efa13fbdeb4506c476c9b3babf6a718da943dab7811c206005a4a956c080c"
|
||||
],
|
||||
"version": "==4.3.0"
|
||||
},
|
||||
"django": {
|
||||
"hashes": [
|
||||
"sha256:0292a7ad7d8ffc9cfc6a77f043d2e81f5bbc360c0c4a1686e130ef3432437d23",
|
||||
"sha256:e89f613e3c1f7ff245ffee3560472f9fa9c07060b11f65e1de3cb763f8dcd4b9"
|
||||
"sha256:25df265e1fdb74f7e7305a1de620a84681bcc9c05e84a3ed97e4a1a63024f18d",
|
||||
"sha256:d6d94554abc82ca37e447c3d28958f5ac39bd7d4adaa285543ae97fb1129fd69"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.0.10"
|
||||
"version": "==2.0.9"
|
||||
},
|
||||
"django-cors-headers": {
|
||||
"hashes": [
|
||||
@@ -141,34 +157,27 @@
|
||||
},
|
||||
"django-extensions": {
|
||||
"hashes": [
|
||||
"sha256:8317a3fe479b1ba3e3a04ecf33fb8d6ccf09bb18f30eab64e34c40a593741d26",
|
||||
"sha256:a76a61566f1c8d96acc7bcf765080b8e91367a25a2c6f8c5bddd574493839180"
|
||||
"sha256:30cb6a8c7d6f75a55edf0c0c4491bd98f8264ae1616ce105f9cecac4387edd07",
|
||||
"sha256:4ad86a7a5e84f1c77db030761ae87a600647250c652030a2b71a16e87f3a3d62"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.1.4"
|
||||
"version": "==2.1.3"
|
||||
},
|
||||
"django-filter": {
|
||||
"hashes": [
|
||||
"sha256:3dafb7d2810790498895c22a1f31b2375795910680ac9c1432821cbedb1e176d",
|
||||
"sha256:a3014de317bef0cd43075a0f08dfa1d319a7ccc5733c3901fb860da70b0dda68"
|
||||
"sha256:6f4e4bc1a11151178520567b50320e5c32f8edb552139d93ea3e30613b886f56",
|
||||
"sha256:86c3925020c27d072cdae7b828aaa5d165c2032a629abbe3c3a1be1edae61c58"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.1.0"
|
||||
},
|
||||
"djangoql": {
|
||||
"hashes": [
|
||||
"sha256:7c488ec4e3362e5389ba3c1169d1ff9a27c4222601f32c6dbf6130ce04330d76"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.12.3"
|
||||
"version": "==2.0.0"
|
||||
},
|
||||
"djangorestframework": {
|
||||
"hashes": [
|
||||
"sha256:79c6efbb2514bc50cf25906d7c0a5cfead714c7af667ff4bd110312cd380ae66",
|
||||
"sha256:a4138613b67e3a223be6c97f53b13d759c5b90d2b433bad670b8ebf95402075f"
|
||||
"sha256:607865b0bb1598b153793892101d881466bd5a991de12bd6229abb18b1c86136",
|
||||
"sha256:63f76cbe1e7d12b94c357d7e54401103b2e52aef0f7c1650d6c820ad708776e5"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==3.9.1"
|
||||
"version": "==3.9.0"
|
||||
},
|
||||
"docopt": {
|
||||
"hashes": [
|
||||
@@ -201,10 +210,10 @@
|
||||
},
|
||||
"faker": {
|
||||
"hashes": [
|
||||
"sha256:16342dca4d92bfc83bab6a7daf6650e0ab087605a66bc38f17523fdb01757910",
|
||||
"sha256:d871ea315b2dcba9138b8344f2c131a76ac62d6227ca39f69b0c889fec97376c"
|
||||
"sha256:2621643b80a10b91999925cfd20f64d2b36f20bf22136bbdc749bb57d6ffe124",
|
||||
"sha256:5ed822d31bd2d6edf10944d176d30dc9c886afdd381eefb7ba8b7aad86171646"
|
||||
],
|
||||
"version": "==1.0.2"
|
||||
"version": "==0.9.2"
|
||||
},
|
||||
"filelock": {
|
||||
"hashes": [
|
||||
@@ -241,10 +250,10 @@
|
||||
},
|
||||
"idna": {
|
||||
"hashes": [
|
||||
"sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
|
||||
"sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
|
||||
"sha256:156a6814fb5ac1fc6850fb002e0852d56c0c8d2531923a51032d1b70760e186e",
|
||||
"sha256:684a38a6f903c1d71d6d5fac066b58d7768af4de2b832e426ec79c30daa94a16"
|
||||
],
|
||||
"version": "==2.8"
|
||||
"version": "==2.7"
|
||||
},
|
||||
"imagesize": {
|
||||
"hashes": [
|
||||
@@ -260,6 +269,28 @@
|
||||
"index": "pypi",
|
||||
"version": "==1.1.8"
|
||||
},
|
||||
"ipython": {
|
||||
"hashes": [
|
||||
"sha256:a5781d6934a3341a1f9acb4ea5acdc7ea0a0855e689dbe755d070ca51e995435",
|
||||
"sha256:b10a7ddd03657c761fc503495bc36471c8158e3fc948573fb9fe82a7029d8efd"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==7.1.1"
|
||||
},
|
||||
"ipython-genutils": {
|
||||
"hashes": [
|
||||
"sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8",
|
||||
"sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8"
|
||||
],
|
||||
"version": "==0.2.0"
|
||||
},
|
||||
"jedi": {
|
||||
"hashes": [
|
||||
"sha256:0191c447165f798e6a730285f2eee783fff81b0d3df261945ecb80983b5c3ca7",
|
||||
"sha256:b7493f73a2febe0dc33d51c99b474547f7f6c0b2c8fb2b21f453eef204c12148"
|
||||
],
|
||||
"version": "==0.13.1"
|
||||
},
|
||||
"jinja2": {
|
||||
"hashes": [
|
||||
"sha256:74c935a1b8bb9a3947c50a54766a969d4846290e1e788ea44c1392163723c3bd",
|
||||
@@ -276,51 +307,31 @@
|
||||
},
|
||||
"markupsafe": {
|
||||
"hashes": [
|
||||
"sha256:048ef924c1623740e70204aa7143ec592504045ae4429b59c30054cb31e3c432",
|
||||
"sha256:130f844e7f5bdd8e9f3f42e7102ef1d49b2e6fdf0d7526df3f87281a532d8c8b",
|
||||
"sha256:19f637c2ac5ae9da8bfd98cef74d64b7e1bb8a63038a3505cd182c3fac5eb4d9",
|
||||
"sha256:1b8a7a87ad1b92bd887568ce54b23565f3fd7018c4180136e1cf412b405a47af",
|
||||
"sha256:1c25694ca680b6919de53a4bb3bdd0602beafc63ff001fea2f2fc16ec3a11834",
|
||||
"sha256:1f19ef5d3908110e1e891deefb5586aae1b49a7440db952454b4e281b41620cd",
|
||||
"sha256:1fa6058938190ebe8290e5cae6c351e14e7bb44505c4a7624555ce57fbbeba0d",
|
||||
"sha256:31cbb1359e8c25f9f48e156e59e2eaad51cd5242c05ed18a8de6dbe85184e4b7",
|
||||
"sha256:3e835d8841ae7863f64e40e19477f7eb398674da6a47f09871673742531e6f4b",
|
||||
"sha256:4e97332c9ce444b0c2c38dd22ddc61c743eb208d916e4265a2a3b575bdccb1d3",
|
||||
"sha256:525396ee324ee2da82919f2ee9c9e73b012f23e7640131dd1b53a90206a0f09c",
|
||||
"sha256:52b07fbc32032c21ad4ab060fec137b76eb804c4b9a1c7c7dc562549306afad2",
|
||||
"sha256:52ccb45e77a1085ec5461cde794e1aa037df79f473cbc69b974e73940655c8d7",
|
||||
"sha256:5c3fbebd7de20ce93103cb3183b47671f2885307df4a17a0ad56a1dd51273d36",
|
||||
"sha256:5e5851969aea17660e55f6a3be00037a25b96a9b44d2083651812c99d53b14d1",
|
||||
"sha256:5edfa27b2d3eefa2210fb2f5d539fbed81722b49f083b2c6566455eb7422fd7e",
|
||||
"sha256:7d263e5770efddf465a9e31b78362d84d015cc894ca2c131901a4445eaa61ee1",
|
||||
"sha256:83381342bfc22b3c8c06f2dd93a505413888694302de25add756254beee8449c",
|
||||
"sha256:857eebb2c1dc60e4219ec8e98dfa19553dae33608237e107db9c6078b1167856",
|
||||
"sha256:98e439297f78fca3a6169fd330fbe88d78b3bb72f967ad9961bcac0d7fdd1550",
|
||||
"sha256:bf54103892a83c64db58125b3f2a43df6d2cb2d28889f14c78519394feb41492",
|
||||
"sha256:d9ac82be533394d341b41d78aca7ed0e0f4ba5a2231602e2f05aa87f25c51672",
|
||||
"sha256:e982fe07ede9fada6ff6705af70514a52beb1b2c3d25d4e873e82114cf3c5401",
|
||||
"sha256:edce2ea7f3dfc981c4ddc97add8a61381d9642dc3273737e756517cc03e84dd6",
|
||||
"sha256:efdc45ef1afc238db84cb4963aa689c0408912a0239b0721cb172b4016eb31d6",
|
||||
"sha256:f137c02498f8b935892d5c0172560d7ab54bc45039de8805075e19079c639a9c",
|
||||
"sha256:f82e347a72f955b7017a39708a3667f106e6ad4d10b25f237396a7115d8ed5fd",
|
||||
"sha256:fb7c206e01ad85ce57feeaaa0bf784b97fa3cad0d4a5737bc5295785f5c613a1"
|
||||
"sha256:a6be69091dac236ea9c6bc7d012beab42010fa914c459791d627dad4910eb665"
|
||||
],
|
||||
"version": "==1.1.0"
|
||||
"version": "==1.0"
|
||||
},
|
||||
"more-itertools": {
|
||||
"hashes": [
|
||||
"sha256:38a936c0a6d98a38bcc2d03fdaaedaba9f412879461dd2ceff8d37564d6522e4",
|
||||
"sha256:c0a5785b1109a6bd7fac76d6837fd1feca158e54e521ccd2ae8bfe393cc9d4fc",
|
||||
"sha256:fe7a7cae1ccb57d33952113ff4fa1bc5f879963600ed74918f1236e212ee50b9"
|
||||
"sha256:c187a73da93e7a8acc0001572aebc7e3c69daf7bf6881a2cea10650bd4420092",
|
||||
"sha256:c476b5d3a34e12d40130bc2f935028b5f636df8f372dc2c1c01dc19681b2039e",
|
||||
"sha256:fcbfeaea0be121980e15bc97b3817b5202ca73d0eae185b4550cbfce2a3ebb3d"
|
||||
],
|
||||
"version": "==5.0.0"
|
||||
"version": "==4.3.0"
|
||||
},
|
||||
"packaging": {
|
||||
"hashes": [
|
||||
"sha256:0c98a5d0be38ed775798ece1b9727178c4469d9c3b4ada66e8e6b7849f8732af",
|
||||
"sha256:9e1cbf8c12b1f1ce0bb5344b8d7ecf66a6f8a6e91bcb0c84593ed6d3ab5c4ab3"
|
||||
"sha256:0886227f54515e592aaa2e5a553332c73962917f2831f1b0f9b9f4380a4b9807",
|
||||
"sha256:f95a1e147590f204328170981833854229bb2912ac3d5f89e2a8ccd2834800c9"
|
||||
],
|
||||
"version": "==19.0"
|
||||
"version": "==18.0"
|
||||
},
|
||||
"parso": {
|
||||
"hashes": [
|
||||
"sha256:35704a43a3c113cce4de228ddb39aab374b8004f4f2407d070b6a2ca784ce8a2",
|
||||
"sha256:895c63e93b94ac1e1690f5fdd40b65f07c8171e3e53cbd7793b5b96c0e0a7f24"
|
||||
],
|
||||
"version": "==0.3.1"
|
||||
},
|
||||
"pdftotext": {
|
||||
"hashes": [
|
||||
@@ -329,91 +340,78 @@
|
||||
"index": "pypi",
|
||||
"version": "==2.1.1"
|
||||
},
|
||||
"pexpect": {
|
||||
"hashes": [
|
||||
"sha256:2a8e88259839571d1251d278476f3eec5db26deb73a70be5ed5dc5435e418aba",
|
||||
"sha256:3fbd41d4caf27fa4a377bfd16fef87271099463e6fa73e92a52f92dfee5d425b"
|
||||
],
|
||||
"markers": "sys_platform != 'win32'",
|
||||
"version": "==4.6.0"
|
||||
},
|
||||
"pickleshare": {
|
||||
"hashes": [
|
||||
"sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca",
|
||||
"sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"
|
||||
],
|
||||
"version": "==0.7.5"
|
||||
},
|
||||
"pillow": {
|
||||
"hashes": [
|
||||
"sha256:051de330a06c99d6f84bcf582960487835bcae3fc99365185dc2d4f65a390c0e",
|
||||
"sha256:0ae5289948c5e0a16574750021bd8be921c27d4e3527800dc9c2c1d2abc81bf7",
|
||||
"sha256:0b1efce03619cdbf8bcc61cfae81fcda59249a469f31c6735ea59badd4a6f58a",
|
||||
"sha256:163136e09bd1d6c6c6026b0a662976e86c58b932b964f255ff384ecc8c3cefa3",
|
||||
"sha256:18e912a6ccddf28defa196bd2021fe33600cbe5da1aa2f2e2c6df15f720b73d1",
|
||||
"sha256:24ec3dea52339a610d34401d2d53d0fb3c7fd08e34b20c95d2ad3973193591f1",
|
||||
"sha256:267f8e4c0a1d7e36e97c6a604f5b03ef58e2b81c1becb4fccecddcb37e063cc7",
|
||||
"sha256:3273a28734175feebbe4d0a4cde04d4ed20f620b9b506d26f44379d3c72304e1",
|
||||
"sha256:4c678e23006798fc8b6f4cef2eaad267d53ff4c1779bd1af8725cc11b72a63f3",
|
||||
"sha256:4d4bc2e6bb6861103ea4655d6b6f67af8e5336e7216e20fff3e18ffa95d7a055",
|
||||
"sha256:505738076350a337c1740a31646e1de09a164c62c07db3b996abdc0f9d2e50cf",
|
||||
"sha256:5233664eadfa342c639b9b9977190d64ad7aca4edc51a966394d7e08e7f38a9f",
|
||||
"sha256:5d95cb9f6cced2628f3e4de7e795e98b2659dfcc7176ab4a01a8b48c2c2f488f",
|
||||
"sha256:7eda4c737637af74bac4b23aa82ea6fbb19002552be85f0b89bc27e3a762d239",
|
||||
"sha256:801ddaa69659b36abf4694fed5aa9f61d1ecf2daaa6c92541bbbbb775d97b9fe",
|
||||
"sha256:825aa6d222ce2c2b90d34a0ea31914e141a85edefc07e17342f1d2fdf121c07c",
|
||||
"sha256:9c215442ff8249d41ff58700e91ef61d74f47dfd431a50253e1a1ca9436b0697",
|
||||
"sha256:a3d90022f2202bbb14da991f26ca7a30b7e4c62bf0f8bf9825603b22d7e87494",
|
||||
"sha256:a631fd36a9823638fe700d9225f9698fb59d049c942d322d4c09544dc2115356",
|
||||
"sha256:a6523a23a205be0fe664b6b8747a5c86d55da960d9586db039eec9f5c269c0e6",
|
||||
"sha256:a756ecf9f4b9b3ed49a680a649af45a8767ad038de39e6c030919c2f443eb000",
|
||||
"sha256:b117287a5bdc81f1bac891187275ec7e829e961b8032c9e5ff38b70fd036c78f",
|
||||
"sha256:ba04f57d1715ca5ff74bb7f8a818bf929a204b3b3c2c2826d1e1cc3b1c13398c",
|
||||
"sha256:cd878195166723f30865e05d87cbaf9421614501a4bd48792c5ed28f90fd36ca",
|
||||
"sha256:cee815cc62d136e96cf76771b9d3eb58e0777ec18ea50de5cfcede8a7c429aa8",
|
||||
"sha256:d1722b7aa4b40cf93ac3c80d3edd48bf93b9208241d166a14ad8e7a20ee1d4f3",
|
||||
"sha256:d7c1c06246b05529f9984435fc4fa5a545ea26606e7f450bdbe00c153f5aeaad",
|
||||
"sha256:e9c8066249c040efdda84793a2a669076f92a301ceabe69202446abb4c5c5ef9",
|
||||
"sha256:f227d7e574d050ff3996049e086e1f18c7bd2d067ef24131e50a1d3fe5831fbc",
|
||||
"sha256:fc9a12aad714af36cf3ad0275a96a733526571e52710319855628f476dcb144e"
|
||||
"sha256:00203f406818c3f45d47bb8fe7e67d3feddb8dcbbd45a289a1de7dd789226360",
|
||||
"sha256:0616f800f348664e694dddb0b0c88d26761dd5e9f34e1ed7b7a7d2da14b40cb7",
|
||||
"sha256:1f7908aab90c92ad85af9d2fec5fc79456a89b3adcc26314d2cde0e238bd789e",
|
||||
"sha256:2ea3517cd5779843de8a759c2349a3cd8d3893e03ab47053b66d5ec6f8bc4f93",
|
||||
"sha256:48a9f0538c91fc136b3a576bee0e7cd174773dc9920b310c21dcb5519722e82c",
|
||||
"sha256:5280ebc42641a1283b7b1f2c20e5b936692198b9dd9995527c18b794850be1a8",
|
||||
"sha256:5e34e4b5764af65551647f5cc67cf5198c1d05621781d5173b342e5e55bf023b",
|
||||
"sha256:63b120421ab85cad909792583f83b6ca3584610c2fe70751e23f606a3c2e87f0",
|
||||
"sha256:696b5e0109fe368d0057f484e2e91717b49a03f1e310f857f133a4acec9f91dd",
|
||||
"sha256:870ed021a42b1b02b5fe4a739ea735f671a84128c0a666c705db2cb9abd528eb",
|
||||
"sha256:916da1c19e4012d06a372127d7140dae894806fad67ef44330e5600d77833581",
|
||||
"sha256:9303a289fa0811e1c6abd9ddebfc770556d7c3311cb2b32eff72164ddc49bc64",
|
||||
"sha256:9577888ecc0ad7d06c3746afaba339c94d62b59da16f7a5d1cff9e491f23dace",
|
||||
"sha256:987e1c94a33c93d9b209315bfda9faa54b8edfce6438a1e93ae866ba20de5956",
|
||||
"sha256:99a3bbdbb844f4fb5d6dd59fac836a40749781c1fa63c563bc216c27aef63f60",
|
||||
"sha256:99db8dc3097ceafbcff9cb2bff384b974795edeb11d167d391a02c7bfeeb6e16",
|
||||
"sha256:a5a96cf49eb580756a44ecf12949e52f211e20bffbf5a95760ac14b1e499cd37",
|
||||
"sha256:aa6ca3eb56704cdc0d876fc6047ffd5ee960caad52452fbee0f99908a141a0ae",
|
||||
"sha256:aade5e66795c94e4a2b2624affeea8979648d1b0ae3fcee17e74e2c647fc4a8a",
|
||||
"sha256:b78905860336c1d292409e3df6ad39cc1f1c7f0964e66844bbc2ebfca434d073",
|
||||
"sha256:b92f521cdc4e4a3041cc343625b699f20b0b5f976793fb45681aac1efda565f8",
|
||||
"sha256:bfde84bbd6ae5f782206d454b67b7ee8f7f818c29b99fd02bf022fd33bab14cb",
|
||||
"sha256:c2b62d3df80e694c0e4a0ed47754c9480521e25642251b3ab1dff050a4e60409",
|
||||
"sha256:c5e2be6c263b64f6f7656e23e18a4a9980cffc671442795682e8c4e4f815dd9f",
|
||||
"sha256:c99aa3c63104e0818ec566f8ff3942fb7c7a8f35f9912cb63fd8e12318b214b2",
|
||||
"sha256:dae06620d3978da346375ebf88b9e2dd7d151335ba668c995aea9ed07af7add4",
|
||||
"sha256:db5499d0710823fa4fb88206050d46544e8f0e0136a9a5f5570b026584c8fd74",
|
||||
"sha256:f36baafd82119c4a114b9518202f2a983819101dcc14b26e43fc12cbefdce00e",
|
||||
"sha256:f52b79c8796d81391ab295b04e520bda6feed54d54931708872e8f9ae9db0ea1",
|
||||
"sha256:ff8cff01582fa1a7e533cb97f628531c4014af4b5f38e33cdcfe5eec29b6d888"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==5.4.1"
|
||||
"version": "==5.3.0"
|
||||
},
|
||||
"pluggy": {
|
||||
"hashes": [
|
||||
"sha256:8ddc32f03971bfdf900a81961a48ccf2fb677cf7715108f85295c67405798616",
|
||||
"sha256:980710797ff6a041e9a73a5787804f848996ecaa6f8a1b1e08224a5894f2074a"
|
||||
"sha256:447ba94990e8014ee25ec853339faf7b0fc8050cdc3289d4d71f7f410fb90095",
|
||||
"sha256:bde19360a8ec4dfd8a20dcb811780a30998101f078fc7ded6162f0076f50508f"
|
||||
],
|
||||
"version": "==0.8.1"
|
||||
"version": "==0.8.0"
|
||||
},
|
||||
"ply": {
|
||||
"prompt-toolkit": {
|
||||
"hashes": [
|
||||
"sha256:00c7c1aaa88358b9c765b6d3000c6eec0ba42abca5351b095321aef446081da3",
|
||||
"sha256:096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce"
|
||||
"sha256:c1d6aff5252ab2ef391c2fe498ed8c088066f66bc64a8d5c095bbf795d9fec34",
|
||||
"sha256:d4c47f79b635a0e70b84fdb97ebd9a274203706b1ee5ed44c10da62755cf3ec9",
|
||||
"sha256:fd17048d8335c1e6d5ee403c3569953ba3eb8555d710bfc548faf0712666ea39"
|
||||
],
|
||||
"version": "==3.11"
|
||||
"version": "==2.0.7"
|
||||
},
|
||||
"psycopg2": {
|
||||
"ptyprocess": {
|
||||
"hashes": [
|
||||
"sha256:02445ebbb3a11a3fe8202c413d5e6faf38bb75b4e336203ee144ca2c46529f94",
|
||||
"sha256:0e9873e60f98f0c52339abf8f0339d1e22bfe5aae0bcf7aabd40c055175035ec",
|
||||
"sha256:1148a5eb29073280bf9057c7fc45468592c1bb75a28f6df1591adb93c8cb63d0",
|
||||
"sha256:259a8324e109d4922b0fcd046e223e289830e2568d6f4132a3702439e5fd532b",
|
||||
"sha256:28dffa9ed4595429e61bacac41d3f9671bb613d1442ff43bcbec63d4f73ed5e8",
|
||||
"sha256:314a74302d4737a3865d40ea50e430ce1543c921ba10f39d562e807cfe2edf2a",
|
||||
"sha256:36b60201b6d215d7658a71493fdf6bd5e60ad9a0cffed39906627ff9f4f3afd3",
|
||||
"sha256:3f9d532bce54c4234161176ff3b8688ff337575ca441ea27597e112dfcd0ee0c",
|
||||
"sha256:5d222983847b40af989ad96c07fc3f07e47925e463baa5de716be8f805b41d9b",
|
||||
"sha256:6757a6d2fc58f7d8f5d471ad180a0bd7b4dd3c7d681f051504fbea7ae29c8d6f",
|
||||
"sha256:6a0e0f1e74edb0ab57d89680e59e7bfefad2bfbdf7c80eb38304d897d43674bb",
|
||||
"sha256:6ca703ccdf734e886a1cf53eb702261110f6a8b0ed74bcad15f1399f74d3f189",
|
||||
"sha256:8513b953d8f443c446aa79a4cc8a898bd415fc5e29349054f03a7d696d495542",
|
||||
"sha256:9262a5ce2038570cb81b4d6413720484cb1bc52c064b2f36228d735b1f98b794",
|
||||
"sha256:97441f851d862a0c844d981cbee7ee62566c322ebb3d68f86d66aa99d483985b",
|
||||
"sha256:a07feade155eb8e69b54dd6774cf6acf2d936660c61d8123b8b6b1f9247b67d6",
|
||||
"sha256:a9b9c02c91b1e3ec1f1886b2d0a90a0ea07cc529cb7e6e472b556bc20ce658f3",
|
||||
"sha256:ae88216f94728d691b945983140bf40d51a1ff6c7fe57def93949bf9339ed54a",
|
||||
"sha256:b360ffd17659491f1a6ad7c928350e229c7b7bd83a2b922b6ee541245c7a776f",
|
||||
"sha256:b4221957ceccf14b2abdabef42d806e791350be10e21b260d7c9ce49012cc19e",
|
||||
"sha256:b90758e49d5e6b152a460d10b92f8a6ccf318fcc0ee814dcf53f3a6fc5328789",
|
||||
"sha256:c669ea986190ed05fb289d0c100cc88064351f2b85177cbfd3564c4f4847d18c",
|
||||
"sha256:d1b61999d15c79cf7f4f7cc9021477aef35277fc52452cf50fd13b713c84424d",
|
||||
"sha256:de7bb043d1adaaf46e38d47e7a5f703bb3dab01376111e522b07d25e1a79c1e1",
|
||||
"sha256:e393568e288d884b94d263f2669215197840d097c7e5b0acd1a51c1ea7d1aba8",
|
||||
"sha256:ed7e0849337bd37d89f2c2b0216a0de863399ee5d363d31b1e5330a99044737b",
|
||||
"sha256:f153f71c3164665d269a5d03c7fa76ba675c7a8de9dc09a4e2c2cdc9936a7b41",
|
||||
"sha256:f1fb5a8427af099beb7f65093cbdb52e021b8e6dbdfaf020402a623f4181baf5",
|
||||
"sha256:f36b333e9f86a2fba960c72b90c34be6ca71819e300f7b1fc3d2b0f0b2c546cd",
|
||||
"sha256:f4526d078aedd5187d0508aa5f9a01eae6a48a470ed678406da94b4cd6524b7e"
|
||||
"sha256:923f299cc5ad920c68f2bc0bc98b75b9f838b93b599941a6b63ddbc2476394c0",
|
||||
"sha256:d7cc528d76e76342423ca640335bd3633420dc1366f258cb31d05e865ef5ca1f"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.7.7"
|
||||
"version": "==0.6.0"
|
||||
},
|
||||
"py": {
|
||||
"hashes": [
|
||||
@@ -432,10 +430,10 @@
|
||||
},
|
||||
"pygments": {
|
||||
"hashes": [
|
||||
"sha256:5ffada19f6203563680669ee7f53b64dabbeb100eb51b61996085e99c03b284a",
|
||||
"sha256:e8218dd399a61674745138520d0d4cf2621d7e032439341bc3f647bff125818d"
|
||||
"sha256:78f3f434bcc5d6ee09020f92ba487f95ba50f1e3ef83ae96b9d5ffa1bab25c5d",
|
||||
"sha256:dbae1046def0efb574852fab9e90209b23f556367b5a320c0bcb871c77c3e8cc"
|
||||
],
|
||||
"version": "==2.3.1"
|
||||
"version": "==2.2.0"
|
||||
},
|
||||
"pyocr": {
|
||||
"hashes": [
|
||||
@@ -446,34 +444,34 @@
|
||||
},
|
||||
"pyparsing": {
|
||||
"hashes": [
|
||||
"sha256:66c9268862641abcac4a96ba74506e594c884e3f57690a696d21ad8210ed667a",
|
||||
"sha256:f6c5ef0d7480ad048c054c37632c67fca55299990fff127850181659eea33fc3"
|
||||
"sha256:40856e74d4987de5d01761a22d1621ae1c7f8774585acae358aa5c5936c6c90b",
|
||||
"sha256:f353aab21fd474459d97b709e527b5571314ee5f067441dc9f88e33eecd96592"
|
||||
],
|
||||
"version": "==2.3.1"
|
||||
"version": "==2.3.0"
|
||||
},
|
||||
"pytest": {
|
||||
"hashes": [
|
||||
"sha256:41568ea7ecb4a68d7f63837cf65b92ce8d0105e43196ff2b26622995bb3dc4b2",
|
||||
"sha256:c3c573a29d7c9547fb90217ece8a8843aa0c1328a797e200290dc3d0b4b823be"
|
||||
"sha256:a9e5e8d7ab9d5b0747f37740276eb362e6a76275d76cebbb52c6049d93b475db",
|
||||
"sha256:bf47e8ed20d03764f963f0070ff1c8fda6e2671fc5dd562a4d3b7148ad60f5ca"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==4.1.1"
|
||||
"version": "==3.9.3"
|
||||
},
|
||||
"pytest-cov": {
|
||||
"hashes": [
|
||||
"sha256:0ab664b25c6aa9716cbf203b17ddb301932383046082c081b9848a0edf5add33",
|
||||
"sha256:230ef817450ab0699c6cc3c9c8f7a829c34674456f2ed8df1fe1d39780f7c87f"
|
||||
"sha256:513c425e931a0344944f84ea47f3956be0e416d95acbd897a44970c8d926d5d7",
|
||||
"sha256:e360f048b7dae3f2f2a9a4d067b2dd6b6a015d384d1577c994a43f3f7cbad762"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.6.1"
|
||||
"version": "==2.6.0"
|
||||
},
|
||||
"pytest-django": {
|
||||
"hashes": [
|
||||
"sha256:1a5d33be930e3172fa238643a380414dc369fe8fa4b3c3de25e59ed142950736",
|
||||
"sha256:e88e471d3d0f9acfb6293bb03d0ee8a33ed978734e92ea6b5312163a6c9e87cc"
|
||||
"sha256:49e9ffc856bc6a1bec1c26c5c7b7213dff7cc8bc6b64d624c4d143d04aff0bcf",
|
||||
"sha256:b379282feaf89069cb790775ab6bbbd2bd2038a68c7ef9b84a41898e0b551081"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==3.4.5"
|
||||
"version": "==3.4.3"
|
||||
},
|
||||
"pytest-env": {
|
||||
"hashes": [
|
||||
@@ -484,26 +482,25 @@
|
||||
},
|
||||
"pytest-forked": {
|
||||
"hashes": [
|
||||
"sha256:260d03fbd38d5ce41a657759e8d19bc7c8cfa6d0dcfa36c0bc9742d33bc30742",
|
||||
"sha256:8d05c2e6f33cd4422571b2b1bb309720c398b0549cff499e3e4cde661875ab54"
|
||||
"sha256:e4500cd0509ec4a26535f7d4112a8cc0f17d3a41c29ffd4eab479d2a55b30805",
|
||||
"sha256:f275cb48a73fc61a6710726348e1da6d68a978f0ec0c54ece5a5fae5977e5a08"
|
||||
],
|
||||
"version": "==1.0.1"
|
||||
"version": "==0.2"
|
||||
},
|
||||
"pytest-sugar": {
|
||||
"hashes": [
|
||||
"sha256:26cf8289fe10880cbbc130bd77398c4e6a8b936d8393b116a5c16121d95ab283",
|
||||
"sha256:fcd87a74b2bce5386d244b49ad60549bfbc4602527797fac167da147983f58ab"
|
||||
"sha256:ab8cc42faf121344a4e9b13f39a51257f26f410e416c52ea11078cdd00d98a2c"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.9.2"
|
||||
"version": "==0.9.1"
|
||||
},
|
||||
"pytest-xdist": {
|
||||
"hashes": [
|
||||
"sha256:107e9db0ee30ead02ca93e7d6d4846675f1b2142234f0eb1cd4d76739cd9ae6f",
|
||||
"sha256:5795f665e112520fa5beab736ad957e7f36ce7d44210f4004be9d99f86529d97"
|
||||
"sha256:3bc9dcb6ff47e607d3c710727cd9996fd7ac1466d405c3b40bb495da99b6b669",
|
||||
"sha256:8e188d13ce6614c7a678179a76f46231199ffdfe6163de031c17e62ffa256917"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.26.0"
|
||||
"version": "==1.24.0"
|
||||
},
|
||||
"python-dateutil": {
|
||||
"hashes": [
|
||||
@@ -515,61 +512,62 @@
|
||||
},
|
||||
"python-dotenv": {
|
||||
"hashes": [
|
||||
"sha256:a84569d0e00d178bc5b957f7ff208bf49287cbf61857c31c258c4a91f571527b",
|
||||
"sha256:c9b1ddd3cdbe75c7d462cb84674d87130f4b948f090f02c7d7144779afb99ae0"
|
||||
"sha256:122290a38ece9fe4f162dc7c95cae3357b983505830a154d3c98ef7f6c6cea77",
|
||||
"sha256:4a205787bc829233de2a823aa328e44fd9996fedb954989a21f1fc67c13d7a77"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.10.1"
|
||||
"version": "==0.9.1"
|
||||
},
|
||||
"python-gnupg": {
|
||||
"hashes": [
|
||||
"sha256:45daf020b370bda13a1429c859fcdff0b766c0576844211446f9266cae97fb0e",
|
||||
"sha256:85c231850a0275c9722f06e34b45a22510b83a6a6e88f93b5ae32ba04c95056c"
|
||||
"sha256:2d158dfc6b54927752b945ebe57e6a0c45da27747fa3b9ae66eccc0d2147ac0d",
|
||||
"sha256:faa69bab58ed0936f0ccf96c99b92369b7a1819305d37dfe5c927d21a437a09d"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.4.4"
|
||||
"version": "==0.4.3"
|
||||
},
|
||||
"python-levenshtein": {
|
||||
"hashes": [
|
||||
"sha256:033a11de5e3d19ea25c9302d11224e1a1898fe5abd23c61c7c360c25195e3eb1"
|
||||
],
|
||||
"markers": "extra == 'speedup'",
|
||||
"version": "==0.12.0"
|
||||
},
|
||||
"pytz": {
|
||||
"hashes": [
|
||||
"sha256:32b0891edff07e28efe91284ed9c31e123d84bea3fd98e1f72be2508f43ef8d9",
|
||||
"sha256:d5f05e487007e29e03409f9398d074e158d920d36eb82eaf66fb1136b0c5374c"
|
||||
"sha256:31cb35c89bd7d333cd32c5f278fca91b523b0834369e757f4c5641ea252236ca",
|
||||
"sha256:8e0f8568c118d3077b46be7d654cc8167fa916092e28320cde048e54bfc9f1e6"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2018.9"
|
||||
"version": "==2018.7"
|
||||
},
|
||||
"regex": {
|
||||
"hashes": [
|
||||
"sha256:0bcd8ab8c812278981df3161db3f94f0ec72f1fa07020173c96f20e74bd7c16a",
|
||||
"sha256:20b1601b887e1073805adda2f8a09bb4c86dc7629c46c0d7bf28444dcb32920d",
|
||||
"sha256:3c4327dd686d2e05b1b3d60a256fbf1c93c53001614ed8acd65453e09d40e10f",
|
||||
"sha256:5e8c6cef2cd964888d5fdf16f3db3dbaaa18c5c5c648161c52c8df065cc26ac5",
|
||||
"sha256:666b03b1c33ef8105f28ecf0fd26f4480931a91a6e30e29e304c1d9eddce2209",
|
||||
"sha256:8afb6ecd80154464b1ad31a93228b63832526f9b0291a82a55287ae15c01de79",
|
||||
"sha256:9326e1c5b9de6e74150bdd424789aecec41c7ecaf9e78bf4c3acfe6868ce1365",
|
||||
"sha256:e06eac198d9c76bcbe52b987b74ead0d353cfaa9f3d8cd907ec984f4bb20ea1e",
|
||||
"sha256:eee007ee39a02cb631b74f89f992766b9d7e952a750166f3e5a5baf8c328c070"
|
||||
"sha256:0ef96690c3d2294155b7d44187ca4a151e45c931cb768e106ba464a9fa64c5da",
|
||||
"sha256:251683e01a3bcacd9188acf0d4caf7b29a3b963c843159311825613ae144cddb",
|
||||
"sha256:3fe15a75fe00f04d1ec16713d55cf1e206077c450267a10b33318756fb8b3f99",
|
||||
"sha256:53a962f9dc28cdf403978a142cb1e054479759ad64d312a999f9f042c25b5c9a",
|
||||
"sha256:8bd1da6a93d32336a5e5432886dd8543004f0591c39b83dbfa60705cccdf414d",
|
||||
"sha256:b5423061918f602e9342b54d746ac31c598d328ecaf4ef0618763e960c926fd4",
|
||||
"sha256:d80ebc65b1f7d0403117f59309c16eac24be6a0bc730b593a79f703462858d94",
|
||||
"sha256:fd8419979639b7de7fb964a13bce3ac47e6fe33043b83de0398c3067986e5659",
|
||||
"sha256:ff2f15b2b0b4b58ba8a1de651780a0d3fd54f96ad6b77dceb77695220e5d7b7a"
|
||||
],
|
||||
"version": "==2019.1.24"
|
||||
"version": "==2018.11.2"
|
||||
},
|
||||
"requests": {
|
||||
"hashes": [
|
||||
"sha256:502a824f31acdacb3a35b6690b5fbf0bc41d63a24a45c4004352b0242707598e",
|
||||
"sha256:7bf2a778576d825600030a110f3c0e3e8edc51dfaafe1c146e39a2027784957b"
|
||||
"sha256:99dcfdaaeb17caf6e526f32b6a7b780461512ab3f1d992187801694cba42770c",
|
||||
"sha256:a84b8c9ab6239b578f22d1c21d51b696dcfe004032bb80ea832398d6909d7279"
|
||||
],
|
||||
"version": "==2.21.0"
|
||||
"version": "==2.20.0"
|
||||
},
|
||||
"six": {
|
||||
"hashes": [
|
||||
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
|
||||
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
|
||||
"sha256:70e8a77beed4562e7f14fe23a786b54f6296e34344c23bc42f07b15018ff98e9",
|
||||
"sha256:832dc0e10feb1aa2c68dcc57dbb658f1c7e65b9b61af69048abc87a2db00a0eb"
|
||||
],
|
||||
"version": "==1.12.0"
|
||||
"version": "==1.11.0"
|
||||
},
|
||||
"snowballstemmer": {
|
||||
"hashes": [
|
||||
@@ -580,11 +578,11 @@
|
||||
},
|
||||
"sphinx": {
|
||||
"hashes": [
|
||||
"sha256:429e3172466df289f0f742471d7e30ba3ee11f3b5aecd9a840480d03f14bcfe5",
|
||||
"sha256:c4cb17ba44acffae3d3209646b6baec1e215cad3065e852c68cc569d4df1b9f8"
|
||||
"sha256:652eb8c566f18823a022bb4b6dbc868d366df332a11a0226b5bc3a798a479f17",
|
||||
"sha256:d222626d8356de702431e813a05c68a35967e3d66c6cd1c2c89539bb179a7464"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.8.3"
|
||||
"version": "==1.8.1"
|
||||
},
|
||||
"sphinxcontrib-websupport": {
|
||||
"hashes": [
|
||||
@@ -615,11 +613,18 @@
|
||||
},
|
||||
"tox": {
|
||||
"hashes": [
|
||||
"sha256:04f8f1aa05de8e76d7a266ccd14e0d665d429977cd42123bc38efa9b59964e9e",
|
||||
"sha256:25ef928babe88c71e3ed3af0c464d1160b01fca2dd1870a5bb26c2dea61a17fc"
|
||||
"sha256:513e32fdf2f9e2d583c2f248f47ba9886428c949f068ac54a0469cac55df5862",
|
||||
"sha256:75fa30e8329b41b664585f5fb837e23ce1d7e6fa1f7811f2be571c990f9d911b"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==3.7.0"
|
||||
"version": "==3.5.3"
|
||||
},
|
||||
"traitlets": {
|
||||
"hashes": [
|
||||
"sha256:9c4bd2d267b7153df9152698efb1050a5d84982d3384a37b2c1f7723ba3e7835",
|
||||
"sha256:c6cb5e6f57c5a9bdaa40fa71ce7b4af30298fbab9ece9815b5d995ab6217c7d9"
|
||||
],
|
||||
"version": "==4.3.2"
|
||||
},
|
||||
"tzlocal": {
|
||||
"hashes": [
|
||||
@@ -636,106 +641,10 @@
|
||||
},
|
||||
"virtualenv": {
|
||||
"hashes": [
|
||||
"sha256:58c359370401e0af817fb0070911e599c5fdc836166306b04fd0f278151ed125",
|
||||
"sha256:729f0bcab430e4ef137646805b5b1d8efbb43fe53d4a0f33328624a84a5121f7"
|
||||
"sha256:686176c23a538ecc56d27ed9d5217abd34644823d6391cbeb232f42bf722baad",
|
||||
"sha256:f899fafcd92e1150f40c8215328be38ff24b519cd95357fa6e78e006c7638208"
|
||||
],
|
||||
"version": "==16.3.0"
|
||||
}
|
||||
},
|
||||
"develop": {
|
||||
"backcall": {
|
||||
"hashes": [
|
||||
"sha256:38ecd85be2c1e78f77fd91700c76e14667dc21e2713b63876c0eb901196e01e4",
|
||||
"sha256:bbbf4b1e5cd2bdb08f915895b51081c041bac22394fdfcfdfbe9f14b77c08bf2"
|
||||
],
|
||||
"version": "==0.1.0"
|
||||
},
|
||||
"decorator": {
|
||||
"hashes": [
|
||||
"sha256:33cd704aea07b4c28b3eb2c97d288a06918275dac0ecebdaf1bc8a48d98adb9e",
|
||||
"sha256:cabb249f4710888a2fc0e13e9a16c343d932033718ff62e1e9bc93a9d3a9122b"
|
||||
],
|
||||
"version": "==4.3.2"
|
||||
},
|
||||
"ipython": {
|
||||
"hashes": [
|
||||
"sha256:6a9496209b76463f1dec126ab928919aaf1f55b38beb9219af3fe202f6bbdd12",
|
||||
"sha256:f69932b1e806b38a7818d9a1e918e5821b685715040b48e59c657b3c7961b742"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==7.2.0"
|
||||
},
|
||||
"ipython-genutils": {
|
||||
"hashes": [
|
||||
"sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8",
|
||||
"sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8"
|
||||
],
|
||||
"version": "==0.2.0"
|
||||
},
|
||||
"jedi": {
|
||||
"hashes": [
|
||||
"sha256:571702b5bd167911fe9036e5039ba67f820d6502832285cde8c881ab2b2149fd",
|
||||
"sha256:c8481b5e59d34a5c7c42e98f6625e633f6ef59353abea6437472c7ec2093f191"
|
||||
],
|
||||
"version": "==0.13.2"
|
||||
},
|
||||
"parso": {
|
||||
"hashes": [
|
||||
"sha256:4b8f9ed80c3a4a3191aa3261505d868aa552dd25649cb13a7d73b6b7315edf2d",
|
||||
"sha256:5a120be2e8863993b597f1c0437efca799e90e0793c98ae5d4e34ebd00140e31"
|
||||
],
|
||||
"version": "==0.3.2"
|
||||
},
|
||||
"pexpect": {
|
||||
"hashes": [
|
||||
"sha256:2a8e88259839571d1251d278476f3eec5db26deb73a70be5ed5dc5435e418aba",
|
||||
"sha256:3fbd41d4caf27fa4a377bfd16fef87271099463e6fa73e92a52f92dfee5d425b"
|
||||
],
|
||||
"markers": "sys_platform != 'win32'",
|
||||
"version": "==4.6.0"
|
||||
},
|
||||
"pickleshare": {
|
||||
"hashes": [
|
||||
"sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca",
|
||||
"sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"
|
||||
],
|
||||
"version": "==0.7.5"
|
||||
},
|
||||
"prompt-toolkit": {
|
||||
"hashes": [
|
||||
"sha256:c1d6aff5252ab2ef391c2fe498ed8c088066f66bc64a8d5c095bbf795d9fec34",
|
||||
"sha256:d4c47f79b635a0e70b84fdb97ebd9a274203706b1ee5ed44c10da62755cf3ec9",
|
||||
"sha256:fd17048d8335c1e6d5ee403c3569953ba3eb8555d710bfc548faf0712666ea39"
|
||||
],
|
||||
"version": "==2.0.7"
|
||||
},
|
||||
"ptyprocess": {
|
||||
"hashes": [
|
||||
"sha256:923f299cc5ad920c68f2bc0bc98b75b9f838b93b599941a6b63ddbc2476394c0",
|
||||
"sha256:d7cc528d76e76342423ca640335bd3633420dc1366f258cb31d05e865ef5ca1f"
|
||||
],
|
||||
"version": "==0.6.0"
|
||||
},
|
||||
"pygments": {
|
||||
"hashes": [
|
||||
"sha256:5ffada19f6203563680669ee7f53b64dabbeb100eb51b61996085e99c03b284a",
|
||||
"sha256:e8218dd399a61674745138520d0d4cf2621d7e032439341bc3f647bff125818d"
|
||||
],
|
||||
"version": "==2.3.1"
|
||||
},
|
||||
"six": {
|
||||
"hashes": [
|
||||
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
|
||||
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
|
||||
],
|
||||
"version": "==1.12.0"
|
||||
},
|
||||
"traitlets": {
|
||||
"hashes": [
|
||||
"sha256:9c4bd2d267b7153df9152698efb1050a5d84982d3384a37b2c1f7723ba3e7835",
|
||||
"sha256:c6cb5e6f57c5a9bdaa40fa71ce7b4af30298fbab9ece9815b5d995ab6217c7d9"
|
||||
],
|
||||
"version": "==4.3.2"
|
||||
"version": "==16.1.0"
|
||||
},
|
||||
"wcwidth": {
|
||||
"hashes": [
|
||||
@@ -744,5 +653,6 @@
|
||||
],
|
||||
"version": "==0.1.7"
|
||||
}
|
||||
}
|
||||
},
|
||||
"develop": {}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
[ [en](README.md) | de | [el](README-el.md) ]
|
||||
*[English](README.md)*<br/>
|
||||
*[Greek](README-el.md)*
|
||||
|
||||
|
||||
# Paperless
|
||||
|
||||
[](https://paperless.readthedocs.org/) [](https://gitter.im/danielquinn/paperless) [](https://travis-ci.org/danielquinn/paperless) [](https://coveralls.io/github/danielquinn/paperless?branch=master) [](https://github.com/danielquinn/paperless/blob/master/THANKS.md)
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
[ [en](README.md) | [de](README-de.md) | el ]
|
||||
*[English](README.md)*<br/>
|
||||
*[German](README-de.md)*
|
||||
|
||||
|
||||
# Paperless
|
||||
|
||||
[](https://paperless.readthedocs.org/) [](https://gitter.im/danielquinn/paperless) [](https://travis-ci.org/danielquinn/paperless) [](https://coveralls.io/github/danielquinn/paperless?branch=master) [](https://github.com/danielquinn/paperless/blob/master/THANKS.md)
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
[ en | [de](README-de.md) | [el](README-el.md) ]
|
||||
*[German](README-de.md)*<br/>
|
||||
*[Greek](README-el.md)*
|
||||
|
||||
|
||||
# Paperless
|
||||
|
||||
[](https://paperless.readthedocs.org/) [](https://gitter.im/danielquinn/paperless) [](https://travis-ci.org/danielquinn/paperless) [](https://coveralls.io/github/danielquinn/paperless?branch=master) [](https://github.com/danielquinn/paperless/blob/master/THANKS.md)
|
||||
|
||||
|
||||
@@ -17,9 +17,6 @@ services:
|
||||
volumes:
|
||||
- data:/usr/src/paperless/data
|
||||
- media:/usr/src/paperless/media
|
||||
# You have to adapt the local path you want the consumption
|
||||
# directory to mount to by modifying the part before the ':'.
|
||||
- ./consume:/consume
|
||||
env_file: docker-compose.env
|
||||
# The reason the line is here is so that the webserver that doesn't do
|
||||
# any text recognition and doesn't have to install unnecessary
|
||||
@@ -39,8 +36,8 @@ services:
|
||||
volumes:
|
||||
- data:/usr/src/paperless/data
|
||||
- media:/usr/src/paperless/media
|
||||
# This should be set to the same value as the consume directory
|
||||
# in the webserver service above.
|
||||
# You have to adapt the local path you want the consumption
|
||||
# directory to mount to by modifying the part before the ':'.
|
||||
- ./consume:/consume
|
||||
# Likewise, you can add a local path to mount a directory for
|
||||
# exporting. This is not strictly needed for paperless to
|
||||
|
||||
@@ -1,35 +1,6 @@
|
||||
Changelog
|
||||
#########
|
||||
|
||||
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
|
||||
a syntax error in ``docker-compose.yml.example`` `#488`_ and added [DjangoQL](https://github.com/ivelum/djangoql),
|
||||
which allows a litany of handy search functionality `#492`_.
|
||||
* `CkuT`_ and `JOKer`_ hacked out a simple, but super-helpful optimisation to
|
||||
how the thumbnails are served up, improving performance considerably `#481`_.
|
||||
* `tsia`_ added a few fields to the tags REST API. `#483`_.
|
||||
* `Brian Cribbs`_ improved the documentation to help people using Paperless
|
||||
over NFS `#484`_.
|
||||
* `Brendan M. Sleight`_ updated the documentation to include a note for setting the
|
||||
``DEBUG`` value. The ``paperless.conf.example`` file was also updated to
|
||||
mirror the project defaults.
|
||||
|
||||
|
||||
2.6.1
|
||||
=====
|
||||
|
||||
* We now have a logo, complete with a favicon :-)
|
||||
* Removed some problematic tests.
|
||||
* Fix the docker-compose example config to include a shared consume volume so
|
||||
that using the push API will work for users of the Docker install. Thanks to
|
||||
`Colin Frei`_ for fixing this in `#466`_.
|
||||
* `khrise`_ submitted a pull request to include the ``added`` property to the
|
||||
REST API `#471`_.
|
||||
|
||||
|
||||
2.6.0
|
||||
=====
|
||||
|
||||
@@ -623,13 +594,7 @@ bulk of the work on this big change.
|
||||
.. _euri10: https://github.com/euri10
|
||||
.. _Ulli: https://github.com/Ulli2k
|
||||
.. _tsia: https://github.com/tsia
|
||||
.. _Sblop: https://github.com/Sblop
|
||||
.. _Colin Frei: https://github.com/colinfrei
|
||||
.. _khrise: https://github.com/khrise
|
||||
.. _syntonym: https://github.com/syntonym
|
||||
.. _JOKer: https://github.com/JOKer
|
||||
.. _Brian Cribbs: https://github.com/cribbstechnolog
|
||||
.. _Brendan M. Sleight: https://github.com/bmsleight
|
||||
.. _Sblop: https://github.com/Sblop
|
||||
|
||||
.. _#20: https://github.com/danielquinn/paperless/issues/20
|
||||
.. _#44: https://github.com/danielquinn/paperless/issues/44
|
||||
@@ -729,15 +694,6 @@ bulk of the work on this big change.
|
||||
.. _#440: https://github.com/danielquinn/paperless/pull/440
|
||||
.. _#441: https://github.com/danielquinn/paperless/pull/441
|
||||
.. _#442: https://github.com/danielquinn/paperless/pull/442
|
||||
.. _#466: https://github.com/danielquinn/paperless/pull/466
|
||||
.. _#471: https://github.com/danielquinn/paperless/pull/471
|
||||
.. _#475: https://github.com/danielquinn/paperless/pull/475
|
||||
.. _#481: https://github.com/danielquinn/paperless/pull/481
|
||||
.. _#483: https://github.com/danielquinn/paperless/pull/483
|
||||
.. _#484: https://github.com/danielquinn/paperless/pull/484
|
||||
.. _#488: https://github.com/danielquinn/paperless/pull/488
|
||||
.. _#489: https://github.com/danielquinn/paperless/pull/489
|
||||
.. _#492: https://github.com/danielquinn/paperless/pull/492
|
||||
|
||||
.. _pipenv: https://docs.pipenv.org/
|
||||
.. _a new home on Docker Hub: https://hub.docker.com/r/danielquinn/paperless/
|
||||
|
||||
20
docs/changelog_jonaswinkler.rst
Normal file
20
docs/changelog_jonaswinkler.rst
Normal file
@@ -0,0 +1,20 @@
|
||||
Changelog (jonaswinkler)
|
||||
########################
|
||||
|
||||
1.0.0
|
||||
=====
|
||||
|
||||
* First release based on paperless 2.6.0
|
||||
* Added: Automatic document classification using neural networks (replaces
|
||||
regex-based tagging)
|
||||
* Added: Document types
|
||||
* Added: Archive serial number allows easy referencing of physical document
|
||||
copies
|
||||
* Added: Inbox tags (added automatically to newly consumed documents)
|
||||
* Added: Document viewer on document edit page
|
||||
* Database backend is now configurable
|
||||
|
||||
1.0.1
|
||||
=====
|
||||
|
||||
* Fixed migration order
|
||||
@@ -46,3 +46,4 @@ Contents
|
||||
contributing
|
||||
scanners
|
||||
changelog
|
||||
changelog_jonaswinkler
|
||||
|
||||
@@ -102,7 +102,7 @@ is similar:
|
||||
$ cd /path/to/project
|
||||
$ git pull
|
||||
$ docker build -t paperless .
|
||||
$ docker-compose run --rm consumer migrate
|
||||
$ docker-compose run --rm comsumer migrate
|
||||
$ docker-compose up -d
|
||||
|
||||
If ``git pull`` doesn't report any changes, there is no need to continue with
|
||||
|
||||
@@ -12,7 +12,6 @@ should work) that has the following software installed:
|
||||
* `Imagemagick`_ version 6.7.5 or higher
|
||||
* `unpaper`_
|
||||
* `libpoppler-cpp-dev`_ PDF rendering library
|
||||
* `optipng`_
|
||||
|
||||
.. _Python3: https://python.org/
|
||||
.. _GNU Privacy Guard: https://gnupg.org
|
||||
@@ -20,7 +19,6 @@ should work) that has the following software installed:
|
||||
.. _Imagemagick: http://imagemagick.org/
|
||||
.. _unpaper: https://www.flameeyes.eu/projects/unpaper
|
||||
.. _libpoppler-cpp-dev: https://poppler.freedesktop.org/
|
||||
.. _optipng: http://optipng.sourceforge.net/
|
||||
|
||||
Notably, you should confirm how you access your Python3 installation. Many
|
||||
Linux distributions will install Python3 in parallel to Python2, using the
|
||||
|
||||
@@ -77,16 +77,12 @@ Standard (Bare Metal)
|
||||
encrypt/decrypt the original documents. Don't worry about defining this
|
||||
if you don't want to use encryption (the default).
|
||||
|
||||
Note also that if you're using the ``runserver`` as mentioned below, you
|
||||
should make sure that PAPERLESS_DEBUG="true" or is just commented out as
|
||||
this is the default.
|
||||
|
||||
4. Initialise the SQLite database with ``./manage.py migrate``.
|
||||
5. Create a user for your Paperless instance with
|
||||
``./manage.py createsuperuser``. Follow the prompts to create your user.
|
||||
6. Start the webserver with ``./manage.py runserver <IP>:<PORT>``.
|
||||
If no specific IP or port is given, the default is ``127.0.0.1:8000`` also
|
||||
known as http://localhost:8000/.
|
||||
If no specifc IP or port are given, the default is ``127.0.0.1:8000``
|
||||
also known as http://localhost:8000/.
|
||||
You should now be able to visit your (empty) installation at
|
||||
`Paperless webserver`_ or whatever you chose before. You can login with the
|
||||
user/pass you created in #5.
|
||||
@@ -147,15 +143,6 @@ Docker Method
|
||||
instructions in comments in the file. The only change that is a hard
|
||||
requirement is to specify where the consumption directory should
|
||||
mount.[#dockercomposeyml]_
|
||||
|
||||
.. caution::
|
||||
|
||||
If you are using NFS mounts for the consume directory you also need to
|
||||
change the command to turn off inotify as it doesn't work with NFS
|
||||
|
||||
`command: ["document_consumer", "--no-inotify"]`
|
||||
|
||||
|
||||
5. Modify ``docker-compose.env`` and adapt the following environment variables:
|
||||
|
||||
``PAPERLESS_PASSPHRASE``
|
||||
|
||||
@@ -214,5 +214,5 @@ This too is done via the ``manage.py`` script:
|
||||
|
||||
That's it. It'll loop over all of the documents in your database and attempt
|
||||
to match all of your tags to them. If one matches, it'll be applied. And
|
||||
don't worry, you can run this as often as you like, it won't double-tag
|
||||
don't worry, you can run this as often as you like, it' won't double-tag
|
||||
a document.
|
||||
|
||||
0
models/.keep
Normal file
0
models/.keep
Normal file
@@ -3,6 +3,16 @@
|
||||
# As this file contains passwords it should only be readable by the user
|
||||
# running paperless.
|
||||
|
||||
###############################################################################
|
||||
#### Database Settings ####
|
||||
###############################################################################
|
||||
|
||||
# By default, sqlite is used as the database backend. This can be changed here.
|
||||
#PAPERLESS_DBENGINE="django.db.backends.postgresql_psycopg2"
|
||||
#PAPERLESS_DBNAME="paperless"
|
||||
#PAPERLESS_DBUSER="paperless"
|
||||
#PAPERLESS_DBPASS="paperless"
|
||||
|
||||
|
||||
###############################################################################
|
||||
#### Paths & Folders ####
|
||||
@@ -38,6 +48,13 @@ PAPERLESS_CONSUMPTION_DIR=""
|
||||
#PAPERLESS_STATIC_URL="/static/"
|
||||
|
||||
|
||||
# You can specify where the document classification model file should be
|
||||
# stored. Make sure that this file is writeable by the user executing the
|
||||
# management command "document_create_classifier" and that the path exists.
|
||||
# The default location is /models/model.pickle wwithin the install folder.
|
||||
#PAPERLESS_MODEL_FILE=/path/to/model/file
|
||||
|
||||
|
||||
# These values are required if you want paperless to check a particular email
|
||||
# box every 10 minutes and attempt to consume documents from there. If you
|
||||
# don't define a HOST, mail checking will just be disabled.
|
||||
@@ -61,7 +78,7 @@ PAPERLESS_EMAIL_SECRET=""
|
||||
|
||||
# Controls whether django's debug mode is enabled. Disable this on production
|
||||
# systems. Debug mode is enabled by default.
|
||||
#PAPERLESS_DEBUG="true"
|
||||
PAPERLESS_DEBUG="false"
|
||||
|
||||
|
||||
# Paperless can be instructed to attempt to encrypt your PDF files with GPG
|
||||
@@ -202,11 +219,6 @@ PAPERLESS_EMAIL_SECRET=""
|
||||
#PAPERLESS_FORGIVING_OCR="false"
|
||||
|
||||
|
||||
# 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.
|
||||
#PAPERLESS_OCR_ALWAYS="false"
|
||||
|
||||
|
||||
###############################################################################
|
||||
#### Interface ####
|
||||
###############################################################################
|
||||
|
||||
@@ -4,67 +4,80 @@ apipkg==1.5
|
||||
atomicwrites==1.2.1
|
||||
attrs==18.2.0
|
||||
babel==2.6.0
|
||||
certifi==2018.11.29
|
||||
backcall==0.1.0
|
||||
certifi==2018.10.15
|
||||
chardet==3.0.4
|
||||
coverage==4.5.2
|
||||
coverage==4.5.1
|
||||
coveralls==1.5.1
|
||||
dateparser==0.7.0
|
||||
decorator==4.3.0
|
||||
django-cors-headers==2.4.0
|
||||
django-crispy-forms==1.7.2
|
||||
django-extensions==2.1.4
|
||||
django-filter==2.1.0
|
||||
django==2.0.10
|
||||
djangoql==0.12.3
|
||||
djangorestframework==3.9.1
|
||||
django-extensions==2.1.3
|
||||
django-filter==2.0.0
|
||||
django==2.0.9
|
||||
djangorestframework==3.9.0
|
||||
docopt==0.6.2
|
||||
docutils==0.14
|
||||
execnet==1.5.0
|
||||
factory-boy==2.11.1
|
||||
faker==1.0.2
|
||||
faker==0.9.2
|
||||
filelock==3.0.10
|
||||
filemagic==1.6
|
||||
fuzzywuzzy[speedup]==0.15.0
|
||||
gunicorn==19.9.0
|
||||
idna==2.8
|
||||
idna==2.7
|
||||
imagesize==1.1.0
|
||||
inotify-simple==1.1.8
|
||||
ipython-genutils==0.2.0
|
||||
ipython==7.1.1
|
||||
jedi==0.13.1
|
||||
jinja2==2.10
|
||||
langdetect==1.0.7
|
||||
markupsafe==1.1.0
|
||||
more-itertools==5.0.0
|
||||
packaging==19.0
|
||||
markupsafe==1.0
|
||||
more-itertools==4.3.0
|
||||
numpy==1.15.1
|
||||
packaging==18.0
|
||||
parso==0.3.1
|
||||
pdftotext==2.1.1
|
||||
pillow==5.4.1
|
||||
pluggy==0.8.1
|
||||
ply==3.11
|
||||
psycopg2==2.7.7
|
||||
pexpect==4.6.0
|
||||
pickleshare==0.7.5
|
||||
pillow==5.3.0
|
||||
pluggy==0.8.0
|
||||
psycopg2==2.7.6.1
|
||||
prompt-toolkit==2.0.7
|
||||
ptyprocess==0.6.0
|
||||
py==1.7.0
|
||||
pycodestyle==2.4.0
|
||||
pygments==2.3.1
|
||||
pygments==2.2.0
|
||||
pyocr==0.5.3
|
||||
pyparsing==2.3.1
|
||||
pytest-cov==2.6.1
|
||||
pytest-django==3.4.5
|
||||
pyparsing==2.3.0
|
||||
pytest-cov==2.6.0
|
||||
pytest-django==3.4.3
|
||||
pytest-env==0.6.2
|
||||
pytest-forked==1.0.1
|
||||
pytest-sugar==0.9.2
|
||||
pytest-xdist==1.26.0
|
||||
pytest==4.1.1
|
||||
pytest-forked==0.2
|
||||
pytest-sugar==0.9.1
|
||||
pytest-xdist==1.24.0
|
||||
pytest==3.9.3
|
||||
python-dateutil==2.7.5
|
||||
python-dotenv==0.10.1
|
||||
python-gnupg==0.4.4
|
||||
python-levenshtein==0.12.0
|
||||
pytz==2018.9
|
||||
regex==2019.1.24
|
||||
requests==2.21.0
|
||||
six==1.12.0
|
||||
python-dotenv==0.9.1
|
||||
python-gnupg==0.4.3
|
||||
python-levenshtein==0.12.0 ; extra == 'speedup'
|
||||
pytz==2018.7
|
||||
regex==2018.11.2
|
||||
requests==2.20.0
|
||||
six==1.11.0
|
||||
scikit-learn==0.19.2
|
||||
scipy==1.1.0
|
||||
snowballstemmer==1.2.1
|
||||
sphinx==1.8.3
|
||||
sphinx==1.8.1
|
||||
sphinxcontrib-websupport==1.1.0
|
||||
termcolor==1.1.0
|
||||
text-unidecode==1.2
|
||||
toml==0.10.0
|
||||
tox==3.7.0
|
||||
tox==3.5.3
|
||||
traitlets==4.3.2
|
||||
tzlocal==1.5.1
|
||||
urllib3==1.24.1
|
||||
virtualenv==16.3.0
|
||||
virtualenv==16.1.0
|
||||
wcwidth==0.1.7
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 91 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 111 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 116 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 94 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 7.4 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 7.5 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 7.5 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 7.4 KiB |
@@ -1,82 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<svg
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
version="1.1"
|
||||
width="900"
|
||||
height="900"
|
||||
id="svg3923"
|
||||
sodipodi:docname="square.svg"
|
||||
inkscape:export-filename="/tmp/test.png"
|
||||
inkscape:export-xdpi="96"
|
||||
inkscape:export-ydpi="96"
|
||||
inkscape:version="0.92.2 2405546, 2018-03-11">
|
||||
<metadata
|
||||
id="metadata3929">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
<dc:title></dc:title>
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<defs
|
||||
id="defs3927" />
|
||||
<sodipodi:namedview
|
||||
pagecolor="#ffffff"
|
||||
bordercolor="#666666"
|
||||
borderopacity="1"
|
||||
objecttolerance="10"
|
||||
gridtolerance="10"
|
||||
guidetolerance="10"
|
||||
inkscape:pageopacity="0"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:window-width="3840"
|
||||
inkscape:window-height="2096"
|
||||
id="namedview3925"
|
||||
showgrid="false"
|
||||
inkscape:zoom="1.1360927"
|
||||
inkscape:cx="635.07139"
|
||||
inkscape:cy="606.383"
|
||||
inkscape:window-x="0"
|
||||
inkscape:window-y="27"
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:current-layer="g3921" />
|
||||
<g
|
||||
transform="matrix(10.638298,0,0,10.638298,106.38298,-206.38301)"
|
||||
id="g3921">
|
||||
<defs
|
||||
id="SvgjsDefs1018" />
|
||||
<g
|
||||
id="SvgjsG1019"
|
||||
featureKey="root"
|
||||
style="fill:#ffffff" />
|
||||
<g
|
||||
id="SvgjsG1020"
|
||||
featureKey="symbol1"
|
||||
transform="matrix(0.10341565,0,0,0.10341565,-11.43874,18.048418)"
|
||||
inkscape:export-filename="/tmp/test.png"
|
||||
inkscape:export-xdpi="116.02285"
|
||||
inkscape:export-ydpi="116.02285"
|
||||
style="fill:#17541f">
|
||||
<defs
|
||||
id="defs3911" />
|
||||
<g
|
||||
id="g3915">
|
||||
<path
|
||||
d="M 231,798 C 227,779 219,741 218,741 49,640 69,465 125,365 c 12,126 235,213 105,367 -1,2 6,26 12,48 26,-44 65,-97 63,-102 C 145,288 645,258 749,16 c 47,234 -24,596 -426,688 -2,1 -73,126 -76,127 0,-2 -30,-1 -26,-11 2,-6 6,-14 10,-22 z M 330,625 C 267,476 452,312 544,271 356,439 324,564 330,625 Z m -104,79 c 51,-59 -9,-160 -45,-193 61,105 57,166 45,193 z"
|
||||
style="fill:#17541f"
|
||||
id="path3913"
|
||||
inkscape:connector-curvature="0" />
|
||||
</g>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 2.6 KiB |
@@ -75,7 +75,7 @@ install_languages() {
|
||||
pkg="tesseract-ocr-data-$lang"
|
||||
|
||||
# English is installed by default
|
||||
if [[ "$lang" == "eng" ]]; then
|
||||
if [ "$lang" == "eng" ]; then
|
||||
continue
|
||||
fi
|
||||
|
||||
@@ -95,7 +95,7 @@ if [[ "$1" != "/"* ]]; then
|
||||
initialize
|
||||
|
||||
# Install additional languages if specified
|
||||
if [[ ! -z "$PAPERLESS_OCR_LANGUAGES" ]]; then
|
||||
if [ ! -z "$PAPERLESS_OCR_LANGUAGES" ]; then
|
||||
install_languages "$PAPERLESS_OCR_LANGUAGES"
|
||||
fi
|
||||
|
||||
|
||||
64
src/documents/actions.py
Normal file → Executable file
64
src/documents/actions.py
Normal file → Executable file
@@ -4,7 +4,8 @@ from django.contrib.admin.utils import model_ngettext
|
||||
from django.core.exceptions import PermissionDenied
|
||||
from django.template.response import TemplateResponse
|
||||
|
||||
from documents.models import Correspondent, Tag
|
||||
from documents.classifier import DocumentClassifier
|
||||
from documents.models import Correspondent, DocumentType, Tag
|
||||
|
||||
|
||||
def select_action(
|
||||
@@ -17,9 +18,9 @@ def select_action(
|
||||
if not modeladmin.has_change_permission(request):
|
||||
raise PermissionDenied
|
||||
|
||||
if request.POST.get('post'):
|
||||
if request.POST.get("post"):
|
||||
n = queryset.count()
|
||||
selected_object = modelclass.objects.get(id=request.POST.get('obj_id'))
|
||||
selected_object = modelclass.objects.get(id=request.POST.get("obj_id"))
|
||||
if n:
|
||||
for document in queryset:
|
||||
if document_action:
|
||||
@@ -137,6 +138,57 @@ def remove_correspondent_from_selected(modeladmin, request, queryset):
|
||||
)
|
||||
|
||||
|
||||
def set_document_type_on_selected(modeladmin, request, queryset):
|
||||
return select_action(
|
||||
modeladmin=modeladmin,
|
||||
request=request,
|
||||
queryset=queryset,
|
||||
title="Set document type on multiple documents",
|
||||
action="set_document_type_on_selected",
|
||||
modelclass=DocumentType,
|
||||
success_message="Successfully set document type %(selected_object)s "
|
||||
"on %(count)d %(items)s.",
|
||||
queryset_action=lambda qs, document_type: qs.update(
|
||||
document_type=document_type)
|
||||
)
|
||||
|
||||
|
||||
def remove_document_type_from_selected(modeladmin, request, queryset):
|
||||
return simple_action(
|
||||
modeladmin=modeladmin,
|
||||
request=request,
|
||||
queryset=queryset,
|
||||
success_message="Successfully removed document type from %(count)d "
|
||||
"%(items)s.",
|
||||
queryset_action=lambda qs: qs.update(document_type=None)
|
||||
)
|
||||
|
||||
|
||||
def run_document_classifier_on_selected(modeladmin, request, queryset):
|
||||
clf = DocumentClassifier()
|
||||
try:
|
||||
clf.reload()
|
||||
return simple_action(
|
||||
modeladmin=modeladmin,
|
||||
request=request,
|
||||
queryset=queryset,
|
||||
success_message="Successfully applied document classifier to "
|
||||
"%(count)d %(items)s.",
|
||||
document_action=lambda doc: clf.classify_document(
|
||||
doc,
|
||||
classify_correspondent=True,
|
||||
classify_tags=True,
|
||||
classify_document_type=True)
|
||||
)
|
||||
except FileNotFoundError:
|
||||
modeladmin.message_user(
|
||||
request,
|
||||
"Classifier model file not found.",
|
||||
messages.ERROR
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
add_tag_to_selected.short_description = "Add tag to selected documents"
|
||||
remove_tag_from_selected.short_description = \
|
||||
"Remove tag from selected documents"
|
||||
@@ -144,3 +196,9 @@ set_correspondent_on_selected.short_description = \
|
||||
"Set correspondent on selected documents"
|
||||
remove_correspondent_from_selected.short_description = \
|
||||
"Remove correspondent from selected documents"
|
||||
set_document_type_on_selected.short_description = \
|
||||
"Set document type on selected documents"
|
||||
remove_document_type_from_selected.short_description = \
|
||||
"Remove document type from selected documents"
|
||||
run_document_classifier_on_selected.short_description = \
|
||||
"Run document classifier on selected"
|
||||
|
||||
54
src/documents/admin.py
Normal file → Executable file
54
src/documents/admin.py
Normal file → Executable file
@@ -11,16 +11,18 @@ from django.urls import reverse
|
||||
from django.utils.html import format_html, format_html_join
|
||||
from django.utils.http import urlquote
|
||||
from django.utils.safestring import mark_safe
|
||||
from djangoql.admin import DjangoQLSearchMixin
|
||||
|
||||
from documents.actions import (
|
||||
add_tag_to_selected,
|
||||
remove_correspondent_from_selected,
|
||||
remove_tag_from_selected,
|
||||
set_correspondent_on_selected
|
||||
set_correspondent_on_selected,
|
||||
set_document_type_on_selected,
|
||||
remove_document_type_from_selected,
|
||||
run_document_classifier_on_selected
|
||||
)
|
||||
|
||||
from .models import Correspondent, Document, Log, Tag
|
||||
from .models import Correspondent, Document, DocumentType, Log, Tag
|
||||
|
||||
|
||||
class FinancialYearFilter(admin.SimpleListFilter):
|
||||
@@ -117,13 +119,11 @@ class CorrespondentAdmin(CommonAdmin):
|
||||
|
||||
list_display = (
|
||||
"name",
|
||||
"match",
|
||||
"matching_algorithm",
|
||||
"automatic_classification",
|
||||
"document_count",
|
||||
"last_correspondence"
|
||||
)
|
||||
list_filter = ("matching_algorithm",)
|
||||
list_editable = ("match", "matching_algorithm")
|
||||
list_editable = ("automatic_classification",)
|
||||
|
||||
readonly_fields = ("slug",)
|
||||
|
||||
@@ -147,9 +147,12 @@ class CorrespondentAdmin(CommonAdmin):
|
||||
class TagAdmin(CommonAdmin):
|
||||
|
||||
list_display = (
|
||||
"name", "colour", "match", "matching_algorithm", "document_count")
|
||||
list_filter = ("colour", "matching_algorithm")
|
||||
list_editable = ("colour", "match", "matching_algorithm")
|
||||
"name",
|
||||
"colour",
|
||||
"automatic_classification",
|
||||
"document_count")
|
||||
list_filter = ("colour",)
|
||||
list_editable = ("colour", "automatic_classification")
|
||||
|
||||
readonly_fields = ("slug",)
|
||||
|
||||
@@ -166,7 +169,24 @@ class TagAdmin(CommonAdmin):
|
||||
document_count.admin_order_field = "document_count"
|
||||
|
||||
|
||||
class DocumentAdmin(DjangoQLSearchMixin, CommonAdmin):
|
||||
class DocumentTypeAdmin(CommonAdmin):
|
||||
|
||||
list_display = ("name", "automatic_classification", "document_count")
|
||||
list_editable = ("automatic_classification",)
|
||||
|
||||
readonly_fields = ("slug",)
|
||||
|
||||
def get_queryset(self, request):
|
||||
qs = super(DocumentTypeAdmin, self).get_queryset(request)
|
||||
qs = qs.annotate(document_count=models.Count("documents"))
|
||||
return qs
|
||||
|
||||
def document_count(self, obj):
|
||||
return obj.document_count
|
||||
document_count.admin_order_field = "document_count"
|
||||
|
||||
|
||||
class DocumentAdmin(CommonAdmin):
|
||||
|
||||
class Media:
|
||||
css = {
|
||||
@@ -176,8 +196,9 @@ class DocumentAdmin(DjangoQLSearchMixin, CommonAdmin):
|
||||
search_fields = ("correspondent__name", "title", "content", "tags__name")
|
||||
readonly_fields = ("added", "file_type", "storage_type",)
|
||||
list_display = ("title", "created", "added", "thumbnail", "correspondent",
|
||||
"tags_")
|
||||
"tags_", "archive_serial_number", "document_type")
|
||||
list_filter = (
|
||||
"document_type",
|
||||
"tags",
|
||||
("correspondent", RecentCorrespondentFilter),
|
||||
FinancialYearFilter
|
||||
@@ -191,7 +212,10 @@ class DocumentAdmin(DjangoQLSearchMixin, CommonAdmin):
|
||||
add_tag_to_selected,
|
||||
remove_tag_from_selected,
|
||||
set_correspondent_on_selected,
|
||||
remove_correspondent_from_selected
|
||||
remove_correspondent_from_selected,
|
||||
set_document_type_on_selected,
|
||||
remove_document_type_from_selected,
|
||||
run_document_classifier_on_selected
|
||||
]
|
||||
|
||||
date_hierarchy = "created"
|
||||
@@ -224,6 +248,9 @@ class DocumentAdmin(DjangoQLSearchMixin, CommonAdmin):
|
||||
extra_context=None):
|
||||
|
||||
extra_context = extra_context or {}
|
||||
doc = Document.objects.get(id=object_id)
|
||||
extra_context["download_url"] = doc.download_url
|
||||
extra_context["file_type"] = doc.file_type
|
||||
|
||||
if self.document_queue and object_id:
|
||||
if int(object_id) in self.document_queue:
|
||||
@@ -347,6 +374,7 @@ class LogAdmin(CommonAdmin):
|
||||
|
||||
admin.site.register(Correspondent, CorrespondentAdmin)
|
||||
admin.site.register(Tag, TagAdmin)
|
||||
admin.site.register(DocumentType, DocumentTypeAdmin)
|
||||
admin.site.register(Document, DocumentAdmin)
|
||||
admin.site.register(Log, LogAdmin)
|
||||
|
||||
|
||||
@@ -11,8 +11,8 @@ class DocumentsConfig(AppConfig):
|
||||
from .signals import document_consumption_started
|
||||
from .signals import document_consumption_finished
|
||||
from .signals.handlers import (
|
||||
set_correspondent,
|
||||
set_tags,
|
||||
classify_document,
|
||||
add_inbox_tags,
|
||||
run_pre_consume_script,
|
||||
run_post_consume_script,
|
||||
cleanup_document_deletion,
|
||||
@@ -21,8 +21,8 @@ class DocumentsConfig(AppConfig):
|
||||
|
||||
document_consumption_started.connect(run_pre_consume_script)
|
||||
|
||||
document_consumption_finished.connect(set_tags)
|
||||
document_consumption_finished.connect(set_correspondent)
|
||||
document_consumption_finished.connect(classify_document)
|
||||
document_consumption_finished.connect(add_inbox_tags)
|
||||
document_consumption_finished.connect(set_log_entry)
|
||||
document_consumption_finished.connect(run_post_consume_script)
|
||||
|
||||
|
||||
240
src/documents/classifier.py
Executable file
240
src/documents/classifier.py
Executable file
@@ -0,0 +1,240 @@
|
||||
import logging
|
||||
import os
|
||||
import pickle
|
||||
|
||||
from sklearn.feature_extraction.text import CountVectorizer
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
from sklearn.preprocessing import MultiLabelBinarizer, LabelBinarizer
|
||||
|
||||
from documents.models import Correspondent, DocumentType, Tag, Document
|
||||
from paperless import settings
|
||||
|
||||
|
||||
def preprocess_content(content):
|
||||
content = content.lower()
|
||||
content = content.strip()
|
||||
content = content.replace("\n", " ")
|
||||
content = content.replace("\r", " ")
|
||||
while content.find(" ") > -1:
|
||||
content = content.replace(" ", " ")
|
||||
return content
|
||||
|
||||
|
||||
class DocumentClassifier(object):
|
||||
|
||||
def __init__(self):
|
||||
self.classifier_version = 0
|
||||
|
||||
self.data_vectorizer = None
|
||||
|
||||
self.tags_binarizer = None
|
||||
self.correspondent_binarizer = None
|
||||
self.document_type_binarizer = None
|
||||
|
||||
self.tags_classifier = None
|
||||
self.correspondent_classifier = None
|
||||
self.document_type_classifier = None
|
||||
|
||||
def reload(self):
|
||||
if os.path.getmtime(settings.MODEL_FILE) > self.classifier_version:
|
||||
logging.getLogger(__name__).info("Reloading classifier models")
|
||||
with open(settings.MODEL_FILE, "rb") as f:
|
||||
self.data_vectorizer = pickle.load(f)
|
||||
self.tags_binarizer = pickle.load(f)
|
||||
self.correspondent_binarizer = pickle.load(f)
|
||||
self.document_type_binarizer = pickle.load(f)
|
||||
|
||||
self.tags_classifier = pickle.load(f)
|
||||
self.correspondent_classifier = pickle.load(f)
|
||||
self.document_type_classifier = pickle.load(f)
|
||||
self.classifier_version = os.path.getmtime(settings.MODEL_FILE)
|
||||
|
||||
def save_classifier(self):
|
||||
with open(settings.MODEL_FILE, "wb") as f:
|
||||
pickle.dump(self.data_vectorizer, f)
|
||||
|
||||
pickle.dump(self.tags_binarizer, f)
|
||||
pickle.dump(self.correspondent_binarizer, f)
|
||||
pickle.dump(self.document_type_binarizer, f)
|
||||
|
||||
pickle.dump(self.tags_classifier, f)
|
||||
pickle.dump(self.correspondent_classifier, f)
|
||||
pickle.dump(self.document_type_classifier, f)
|
||||
|
||||
def train(self):
|
||||
data = list()
|
||||
labels_tags = list()
|
||||
labels_correspondent = list()
|
||||
labels_document_type = list()
|
||||
|
||||
# Step 1: Extract and preprocess training data from the database.
|
||||
logging.getLogger(__name__).info("Gathering data from database...")
|
||||
for doc in Document.objects.exclude(tags__is_inbox_tag=True):
|
||||
data.append(preprocess_content(doc.content))
|
||||
|
||||
y = -1
|
||||
if doc.document_type:
|
||||
if doc.document_type.automatic_classification:
|
||||
y = doc.document_type.id
|
||||
labels_document_type.append(y)
|
||||
|
||||
y = -1
|
||||
if doc.correspondent:
|
||||
if doc.correspondent.automatic_classification:
|
||||
y = doc.correspondent.id
|
||||
labels_correspondent.append(y)
|
||||
|
||||
tags = [tag.id for tag in doc.tags.filter(
|
||||
automatic_classification=True
|
||||
)]
|
||||
labels_tags.append(tags)
|
||||
|
||||
labels_tags_unique = set([tag for tags in labels_tags for tag in tags])
|
||||
logging.getLogger(__name__).info(
|
||||
"{} documents, {} tag(s), {} correspondent(s), "
|
||||
"{} document type(s).".format(
|
||||
len(data),
|
||||
len(labels_tags_unique),
|
||||
len(set(labels_correspondent)),
|
||||
len(set(labels_document_type))
|
||||
)
|
||||
)
|
||||
|
||||
# Step 2: vectorize data
|
||||
logging.getLogger(__name__).info("Vectorizing data...")
|
||||
self.data_vectorizer = CountVectorizer(
|
||||
analyzer="char",
|
||||
ngram_range=(3, 5),
|
||||
min_df=0.1
|
||||
)
|
||||
data_vectorized = self.data_vectorizer.fit_transform(data)
|
||||
|
||||
self.tags_binarizer = MultiLabelBinarizer()
|
||||
labels_tags_vectorized = self.tags_binarizer.fit_transform(labels_tags)
|
||||
|
||||
self.correspondent_binarizer = LabelBinarizer()
|
||||
labels_correspondent_vectorized = \
|
||||
self.correspondent_binarizer.fit_transform(labels_correspondent)
|
||||
|
||||
self.document_type_binarizer = LabelBinarizer()
|
||||
labels_document_type_vectorized = \
|
||||
self.document_type_binarizer.fit_transform(labels_document_type)
|
||||
|
||||
# Step 3: train the classifiers
|
||||
if len(self.tags_binarizer.classes_) > 0:
|
||||
logging.getLogger(__name__).info("Training tags classifier...")
|
||||
self.tags_classifier = MLPClassifier(verbose=True)
|
||||
self.tags_classifier.fit(data_vectorized, labels_tags_vectorized)
|
||||
else:
|
||||
self.tags_classifier = None
|
||||
logging.getLogger(__name__).info(
|
||||
"There are no tags. Not training tags classifier."
|
||||
)
|
||||
|
||||
if len(self.correspondent_binarizer.classes_) > 0:
|
||||
logging.getLogger(__name__).info(
|
||||
"Training correspondent classifier..."
|
||||
)
|
||||
self.correspondent_classifier = MLPClassifier(verbose=True)
|
||||
self.correspondent_classifier.fit(
|
||||
data_vectorized,
|
||||
labels_correspondent_vectorized
|
||||
)
|
||||
else:
|
||||
self.correspondent_classifier = None
|
||||
logging.getLogger(__name__).info(
|
||||
"There are no correspondents. Not training correspondent "
|
||||
"classifier."
|
||||
)
|
||||
|
||||
if len(self.document_type_binarizer.classes_) > 0:
|
||||
logging.getLogger(__name__).info(
|
||||
"Training document type classifier..."
|
||||
)
|
||||
self.document_type_classifier = MLPClassifier(verbose=True)
|
||||
self.document_type_classifier.fit(
|
||||
data_vectorized,
|
||||
labels_document_type_vectorized
|
||||
)
|
||||
else:
|
||||
self.document_type_classifier = None
|
||||
logging.getLogger(__name__).info(
|
||||
"There are no document types. Not training document type "
|
||||
"classifier."
|
||||
)
|
||||
|
||||
def classify_document(
|
||||
self, document, classify_correspondent=False,
|
||||
classify_document_type=False, classify_tags=False,
|
||||
replace_tags=False):
|
||||
|
||||
X = self.data_vectorizer.transform(
|
||||
[preprocess_content(document.content)]
|
||||
)
|
||||
|
||||
if classify_correspondent and self.correspondent_classifier:
|
||||
self._classify_correspondent(X, document)
|
||||
|
||||
if classify_document_type and self.document_type_classifier:
|
||||
self._classify_document_type(X, document)
|
||||
|
||||
if classify_tags and self.tags_classifier:
|
||||
self._classify_tags(X, document, replace_tags)
|
||||
|
||||
document.save(update_fields=("correspondent", "document_type"))
|
||||
|
||||
def _classify_correspondent(self, X, document):
|
||||
y = self.correspondent_classifier.predict(X)
|
||||
correspondent_id = self.correspondent_binarizer.inverse_transform(y)[0]
|
||||
try:
|
||||
correspondent = None
|
||||
if correspondent_id != -1:
|
||||
correspondent = Correspondent.objects.get(id=correspondent_id)
|
||||
logging.getLogger(__name__).info(
|
||||
"Detected correspondent: {}".format(correspondent.name)
|
||||
)
|
||||
else:
|
||||
logging.getLogger(__name__).info("Detected correspondent: -")
|
||||
document.correspondent = correspondent
|
||||
except Correspondent.DoesNotExist:
|
||||
logging.getLogger(__name__).warning(
|
||||
"Detected correspondent with id {} does not exist "
|
||||
"anymore! Did you delete it?".format(correspondent_id)
|
||||
)
|
||||
|
||||
def _classify_document_type(self, X, document):
|
||||
y = self.document_type_classifier.predict(X)
|
||||
document_type_id = self.document_type_binarizer.inverse_transform(y)[0]
|
||||
try:
|
||||
document_type = None
|
||||
if document_type_id != -1:
|
||||
document_type = DocumentType.objects.get(id=document_type_id)
|
||||
logging.getLogger(__name__).info(
|
||||
"Detected document type: {}".format(document_type.name)
|
||||
)
|
||||
else:
|
||||
logging.getLogger(__name__).info("Detected document type: -")
|
||||
document.document_type = document_type
|
||||
except DocumentType.DoesNotExist:
|
||||
logging.getLogger(__name__).warning(
|
||||
"Detected document type with id {} does not exist "
|
||||
"anymore! Did you delete it?".format(document_type_id)
|
||||
)
|
||||
|
||||
def _classify_tags(self, X, document, replace_tags):
|
||||
y = self.tags_classifier.predict(X)
|
||||
tags_ids = self.tags_binarizer.inverse_transform(y)[0]
|
||||
if replace_tags:
|
||||
document.tags.clear()
|
||||
for tag_id in tags_ids:
|
||||
try:
|
||||
tag = Tag.objects.get(id=tag_id)
|
||||
logging.getLogger(__name__).info(
|
||||
"Detected tag: {}".format(tag.name)
|
||||
)
|
||||
document.tags.add(tag)
|
||||
except Tag.DoesNotExist:
|
||||
logging.getLogger(__name__).warning(
|
||||
"Detected tag with id {} does not exist anymore! Did "
|
||||
"you delete it?".format(tag_id)
|
||||
)
|
||||
2
src/documents/consumer.py
Normal file → Executable file
2
src/documents/consumer.py
Normal file → Executable file
@@ -225,7 +225,7 @@ class Consumer:
|
||||
storage_type=self.storage_type
|
||||
)
|
||||
|
||||
relevant_tags = set(list(Tag.match_all(text)) + list(file_info.tags))
|
||||
relevant_tags = set(file_info.tags)
|
||||
if relevant_tags:
|
||||
tag_names = ", ".join([t.slug for t in relevant_tags])
|
||||
self.log("debug", "Tagging with {}".format(tag_names))
|
||||
|
||||
18
src/documents/filters.py
Normal file → Executable file
18
src/documents/filters.py
Normal file → Executable file
@@ -1,6 +1,6 @@
|
||||
from django_filters.rest_framework import BooleanFilter, FilterSet
|
||||
|
||||
from .models import Correspondent, Document, Tag
|
||||
from .models import Correspondent, Document, Tag, DocumentType
|
||||
|
||||
|
||||
CHAR_KWARGS = (
|
||||
@@ -35,6 +35,19 @@ class TagFilterSet(FilterSet):
|
||||
}
|
||||
|
||||
|
||||
class DocumentTypeFilterSet(FilterSet):
|
||||
|
||||
class Meta:
|
||||
model = DocumentType
|
||||
fields = {
|
||||
"name": [
|
||||
"startswith", "endswith", "contains",
|
||||
"istartswith", "iendswith", "icontains"
|
||||
],
|
||||
"slug": ["istartswith", "iendswith", "icontains"]
|
||||
}
|
||||
|
||||
|
||||
class DocumentFilterSet(FilterSet):
|
||||
|
||||
tags_empty = BooleanFilter(
|
||||
@@ -57,4 +70,7 @@ class DocumentFilterSet(FilterSet):
|
||||
"tags__name": CHAR_KWARGS,
|
||||
"tags__slug": CHAR_KWARGS,
|
||||
|
||||
"document_type__name": CHAR_KWARGS,
|
||||
"document_type__slug": CHAR_KWARGS,
|
||||
|
||||
}
|
||||
|
||||
@@ -216,11 +216,7 @@ class MailFetcher(Loggable):
|
||||
return r
|
||||
|
||||
def _connect(self):
|
||||
try:
|
||||
self._connection = imaplib.IMAP4_SSL(self._host, self._port)
|
||||
except OSError as e:
|
||||
msg = "Problem connecting to {}: {}".format(self._host, e.strerror)
|
||||
raise MailFetcherError(msg)
|
||||
self._connection = imaplib.IMAP4_SSL(self._host, self._port)
|
||||
|
||||
def _login(self):
|
||||
|
||||
|
||||
@@ -1,82 +0,0 @@
|
||||
import sys
|
||||
|
||||
from django.core.management.base import BaseCommand
|
||||
|
||||
from documents.models import Correspondent, Document
|
||||
|
||||
from ...mixins import Renderable
|
||||
|
||||
|
||||
class Command(Renderable, BaseCommand):
|
||||
|
||||
help = """
|
||||
Using the current set of correspondent rules, apply said rules to all
|
||||
documents in the database, effectively allowing you to back-tag all
|
||||
previously indexed documents with correspondent created (or modified)
|
||||
after their initial import.
|
||||
""".replace(" ", "")
|
||||
|
||||
TOO_MANY_CONTINUE = (
|
||||
"Detected {} potential correspondents for {}, so we've opted for {}")
|
||||
TOO_MANY_SKIP = (
|
||||
"Detected {} potential correspondents for {}, so we're skipping it")
|
||||
CHANGE_MESSAGE = (
|
||||
'Document {}: "{}" was given the correspondent id {}: "{}"')
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.verbosity = 0
|
||||
BaseCommand.__init__(self, *args, **kwargs)
|
||||
|
||||
def add_arguments(self, parser):
|
||||
parser.add_argument(
|
||||
"--use-first",
|
||||
default=False,
|
||||
action="store_true",
|
||||
help="By default this command won't try to assign a correspondent "
|
||||
"if more than one matches the document. Use this flag if "
|
||||
"you'd rather it just pick the first one it finds."
|
||||
)
|
||||
|
||||
def handle(self, *args, **options):
|
||||
|
||||
self.verbosity = options["verbosity"]
|
||||
|
||||
for document in Document.objects.filter(correspondent__isnull=True):
|
||||
|
||||
potential_correspondents = list(
|
||||
Correspondent.match_all(document.content))
|
||||
|
||||
if not potential_correspondents:
|
||||
continue
|
||||
|
||||
potential_count = len(potential_correspondents)
|
||||
correspondent = potential_correspondents[0]
|
||||
|
||||
if potential_count > 1:
|
||||
if not options["use_first"]:
|
||||
print(
|
||||
self.TOO_MANY_SKIP.format(potential_count, document),
|
||||
file=sys.stderr
|
||||
)
|
||||
continue
|
||||
print(
|
||||
self.TOO_MANY_CONTINUE.format(
|
||||
potential_count,
|
||||
document,
|
||||
correspondent
|
||||
),
|
||||
file=sys.stderr
|
||||
)
|
||||
|
||||
document.correspondent = correspondent
|
||||
document.save(update_fields=("correspondent",))
|
||||
|
||||
print(
|
||||
self.CHANGE_MESSAGE.format(
|
||||
document.pk,
|
||||
document.title,
|
||||
correspondent.pk,
|
||||
correspondent.name
|
||||
),
|
||||
file=sys.stderr
|
||||
)
|
||||
25
src/documents/management/commands/document_create_classifier.py
Executable file
25
src/documents/management/commands/document_create_classifier.py
Executable file
@@ -0,0 +1,25 @@
|
||||
import logging
|
||||
|
||||
from django.core.management.base import BaseCommand
|
||||
from documents.classifier import DocumentClassifier
|
||||
from paperless import settings
|
||||
from ...mixins import Renderable
|
||||
|
||||
|
||||
class Command(Renderable, BaseCommand):
|
||||
|
||||
help = """
|
||||
Trains the classifier on your data and saves the resulting models to a
|
||||
file. The document consumer will then automatically use this new model.
|
||||
""".replace(" ", "")
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
BaseCommand.__init__(self, *args, **kwargs)
|
||||
|
||||
def handle(self, *args, **options):
|
||||
clf = DocumentClassifier()
|
||||
clf.train()
|
||||
logging.getLogger(__name__).info(
|
||||
"Saving models to {}...".format(settings.MODEL_FILE)
|
||||
)
|
||||
clf.save_classifier()
|
||||
@@ -6,7 +6,7 @@ import shutil
|
||||
from django.core.management.base import BaseCommand, CommandError
|
||||
from django.core import serializers
|
||||
|
||||
from documents.models import Document, Correspondent, Tag
|
||||
from documents.models import Document, Correspondent, Tag, DocumentType
|
||||
from paperless.db import GnuPG
|
||||
|
||||
from ...mixins import Renderable
|
||||
@@ -96,6 +96,9 @@ class Command(Renderable, BaseCommand):
|
||||
manifest += json.loads(serializers.serialize(
|
||||
"json", Tag.objects.all()))
|
||||
|
||||
manifest += json.loads(serializers.serialize(
|
||||
"json", DocumentType.objects.all()))
|
||||
|
||||
with open(os.path.join(self.target, "manifest.json"), "w") as f:
|
||||
json.dump(manifest, f, indent=2)
|
||||
|
||||
|
||||
64
src/documents/management/commands/document_retagger.py
Normal file → Executable file
64
src/documents/management/commands/document_retagger.py
Normal file → Executable file
@@ -1,5 +1,8 @@
|
||||
import logging
|
||||
|
||||
from django.core.management.base import BaseCommand
|
||||
|
||||
from documents.classifier import DocumentClassifier
|
||||
from documents.models import Document, Tag
|
||||
|
||||
from ...mixins import Renderable
|
||||
@@ -8,25 +11,66 @@ from ...mixins import Renderable
|
||||
class Command(Renderable, BaseCommand):
|
||||
|
||||
help = """
|
||||
Using the current set of tagging rules, apply said rules to all
|
||||
documents in the database, effectively allowing you to back-tag all
|
||||
previously indexed documents with tags created (or modified) after
|
||||
their initial import.
|
||||
Using the current classification model, assigns correspondents, tags
|
||||
and document types to all documents, effectively allowing you to
|
||||
back-tag all previously indexed documents with metadata created (or
|
||||
modified) after their initial import.
|
||||
""".replace(" ", "")
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.verbosity = 0
|
||||
BaseCommand.__init__(self, *args, **kwargs)
|
||||
|
||||
def add_arguments(self, parser):
|
||||
parser.add_argument(
|
||||
"-c", "--correspondent",
|
||||
action="store_true"
|
||||
)
|
||||
parser.add_argument(
|
||||
"-T", "--tags",
|
||||
action="store_true"
|
||||
)
|
||||
parser.add_argument(
|
||||
"-t", "--type",
|
||||
action="store_true"
|
||||
)
|
||||
parser.add_argument(
|
||||
"-i", "--inbox-only",
|
||||
action="store_true"
|
||||
)
|
||||
parser.add_argument(
|
||||
"-r", "--replace-tags",
|
||||
action="store_true"
|
||||
)
|
||||
|
||||
def handle(self, *args, **options):
|
||||
|
||||
self.verbosity = options["verbosity"]
|
||||
|
||||
for document in Document.objects.all():
|
||||
if options["inbox_only"]:
|
||||
queryset = Document.objects.filter(tags__is_inbox_tag=True)
|
||||
else:
|
||||
queryset = Document.objects.all()
|
||||
documents = queryset.distinct()
|
||||
|
||||
tags = Tag.objects.exclude(
|
||||
pk__in=document.tags.values_list("pk", flat=True))
|
||||
logging.getLogger(__name__).info("Loading classifier")
|
||||
clf = DocumentClassifier()
|
||||
try:
|
||||
clf.reload()
|
||||
except FileNotFoundError:
|
||||
logging.getLogger(__name__).fatal("Cannot classify documents, "
|
||||
"classifier model file was not "
|
||||
"found.")
|
||||
return
|
||||
|
||||
for tag in Tag.match_all(document.content, tags):
|
||||
print('Tagging {} with "{}"'.format(document, tag))
|
||||
document.tags.add(tag)
|
||||
for document in documents:
|
||||
logging.getLogger(__name__).info(
|
||||
"Processing document {}".format(document.title)
|
||||
)
|
||||
clf.classify_document(
|
||||
document,
|
||||
classify_document_type=options["type"],
|
||||
classify_tags=options["tags"],
|
||||
classify_correspondent=options["correspondent"],
|
||||
replace_tags=options["replace_tags"]
|
||||
)
|
||||
|
||||
@@ -12,8 +12,9 @@ def re_slug_all_the_things(apps, schema_editor):
|
||||
|
||||
Tag = apps.get_model("documents", "Tag")
|
||||
Correspondent = apps.get_model("documents", "Correspondent")
|
||||
DocumentType = apps.get_model("documents", "DocumentType")
|
||||
|
||||
for klass in (Tag, Correspondent):
|
||||
for klass in (Tag, Correspondent, DocumentType):
|
||||
for instance in klass.objects.all():
|
||||
klass.objects.filter(
|
||||
pk=instance.pk
|
||||
@@ -25,7 +26,7 @@ def re_slug_all_the_things(apps, schema_editor):
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
('documents', '0021_document_storage_type'),
|
||||
('documents', '1003_auto_20180904_1425'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
@@ -48,5 +49,10 @@ class Migration(migrations.Migration):
|
||||
name='slug',
|
||||
field=models.SlugField(blank=True, editable=False),
|
||||
),
|
||||
migrations.AlterField(
|
||||
model_name='documenttype',
|
||||
name='slug',
|
||||
field=models.SlugField(blank=True, editable=False),
|
||||
),
|
||||
migrations.RunPython(re_slug_all_the_things, migrations.RunPython.noop)
|
||||
]
|
||||
|
||||
23
src/documents/migrations/1001_workflow_improvements.py
Executable file
23
src/documents/migrations/1001_workflow_improvements.py
Executable file
@@ -0,0 +1,23 @@
|
||||
# Generated by Django 2.0.7 on 2018-07-12 09:52
|
||||
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
('documents', '0021_document_storage_type'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name='document',
|
||||
name='archive_serial_number',
|
||||
field=models.IntegerField(blank=True, db_index=True, help_text='The position of this document in your physical document archive.', null=True, unique=True),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name='tag',
|
||||
name='is_inbox_tag',
|
||||
field=models.BooleanField(default=False, help_text='Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.'),
|
||||
),
|
||||
]
|
||||
33
src/documents/migrations/1002_auto_20180823_1155.py
Normal file
33
src/documents/migrations/1002_auto_20180823_1155.py
Normal file
@@ -0,0 +1,33 @@
|
||||
# Generated by Django 2.0.7 on 2018-08-23 11:55
|
||||
|
||||
from django.db import migrations, models
|
||||
import django.db.models.deletion
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
('documents', '1001_workflow_improvements'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name='DocumentType',
|
||||
fields=[
|
||||
('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
||||
('name', models.CharField(max_length=128, unique=True)),
|
||||
('slug', models.SlugField(blank=True)),
|
||||
('match', models.CharField(blank=True, max_length=256)),
|
||||
('matching_algorithm', models.PositiveIntegerField(choices=[(1, 'Any'), (2, 'All'), (3, 'Literal'), (4, 'Regular Expression'), (5, 'Fuzzy Match')], default=1, help_text='Which algorithm you want to use when matching text to the OCR\'d PDF. Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided. A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF. (If you don\'t know what a regex is, you probably don\'t want this option.) Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.')),
|
||||
('is_insensitive', models.BooleanField(default=True)),
|
||||
],
|
||||
options={
|
||||
'abstract': False,
|
||||
},
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name='document',
|
||||
name='document_type',
|
||||
field=models.ForeignKey(blank=True, null=True, on_delete=django.db.models.deletion.SET_NULL, related_name='documents', to='documents.DocumentType'),
|
||||
),
|
||||
]
|
||||
77
src/documents/migrations/1003_auto_20180904_1425.py
Normal file
77
src/documents/migrations/1003_auto_20180904_1425.py
Normal file
@@ -0,0 +1,77 @@
|
||||
# Generated by Django 2.0.8 on 2018-09-04 14:25
|
||||
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
def transfer_automatic_classification(apps, schema_editor):
|
||||
for model_name in ["Tag", "Correspondent", "DocumentType"]:
|
||||
model_class = apps.get_model("documents", model_name)
|
||||
for o in model_class.objects.all():
|
||||
o.automatic_classification = o.match is not None and len(o.match) > 0
|
||||
o.save()
|
||||
|
||||
|
||||
def reverse_automatic_classification(apps, schema_editor):
|
||||
pass
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
('documents', '1002_auto_20180823_1155'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name='correspondent',
|
||||
name='automatic_classification',
|
||||
field=models.BooleanField(default=False, help_text='Automatically assign to newly added documents based on current usage in your document collection.'),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name='documenttype',
|
||||
name='automatic_classification',
|
||||
field=models.BooleanField(default=False, help_text='Automatically assign to newly added documents based on current usage in your document collection.'),
|
||||
),
|
||||
migrations.AddField(
|
||||
model_name='tag',
|
||||
name='automatic_classification',
|
||||
field=models.BooleanField(default=False, help_text='Automatically assign to newly added documents based on current usage in your document collection.'),
|
||||
),
|
||||
migrations.RunPython(transfer_automatic_classification, reverse_automatic_classification),
|
||||
migrations.RemoveField(
|
||||
model_name='correspondent',
|
||||
name='is_insensitive',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='correspondent',
|
||||
name='match',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='correspondent',
|
||||
name='matching_algorithm',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='documenttype',
|
||||
name='is_insensitive',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='documenttype',
|
||||
name='match',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='documenttype',
|
||||
name='matching_algorithm',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='tag',
|
||||
name='is_insensitive',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='tag',
|
||||
name='match',
|
||||
),
|
||||
migrations.RemoveField(
|
||||
model_name='tag',
|
||||
name='matching_algorithm',
|
||||
),
|
||||
]
|
||||
0
src/documents/mixins.py
Normal file → Executable file
0
src/documents/mixins.py
Normal file → Executable file
142
src/documents/models.py
Normal file → Executable file
142
src/documents/models.py
Normal file → Executable file
@@ -24,43 +24,15 @@ except ImportError:
|
||||
|
||||
class MatchingModel(models.Model):
|
||||
|
||||
MATCH_ANY = 1
|
||||
MATCH_ALL = 2
|
||||
MATCH_LITERAL = 3
|
||||
MATCH_REGEX = 4
|
||||
MATCH_FUZZY = 5
|
||||
MATCHING_ALGORITHMS = (
|
||||
(MATCH_ANY, "Any"),
|
||||
(MATCH_ALL, "All"),
|
||||
(MATCH_LITERAL, "Literal"),
|
||||
(MATCH_REGEX, "Regular Expression"),
|
||||
(MATCH_FUZZY, "Fuzzy Match"),
|
||||
)
|
||||
|
||||
name = models.CharField(max_length=128, unique=True)
|
||||
slug = models.SlugField(blank=True, editable=False)
|
||||
|
||||
match = models.CharField(max_length=256, blank=True)
|
||||
matching_algorithm = models.PositiveIntegerField(
|
||||
choices=MATCHING_ALGORITHMS,
|
||||
default=MATCH_ANY,
|
||||
help_text=(
|
||||
"Which algorithm you want to use when matching text to the OCR'd "
|
||||
"PDF. Here, \"any\" looks for any occurrence of any word "
|
||||
"provided in the PDF, while \"all\" requires that every word "
|
||||
"provided appear in the PDF, albeit not in the order provided. A "
|
||||
"\"literal\" match means that the text you enter must appear in "
|
||||
"the PDF exactly as you've entered it, and \"regular expression\" "
|
||||
"uses a regex to match the PDF. (If you don't know what a regex "
|
||||
"is, you probably don't want this option.) Finally, a \"fuzzy "
|
||||
"match\" looks for words or phrases that are mostly—but not "
|
||||
"exactly—the same, which can be useful for matching against "
|
||||
"documents containg imperfections that foil accurate OCR."
|
||||
)
|
||||
automatic_classification = models.BooleanField(
|
||||
default=False,
|
||||
help_text="Automatically assign to newly added documents based on "
|
||||
"current usage in your document collection."
|
||||
)
|
||||
|
||||
is_insensitive = models.BooleanField(default=True)
|
||||
|
||||
class Meta:
|
||||
abstract = True
|
||||
ordering = ("name",)
|
||||
@@ -68,86 +40,8 @@ class MatchingModel(models.Model):
|
||||
def __str__(self):
|
||||
return self.name
|
||||
|
||||
@property
|
||||
def conditions(self):
|
||||
return "{}: \"{}\" ({})".format(
|
||||
self.name, self.match, self.get_matching_algorithm_display())
|
||||
|
||||
@classmethod
|
||||
def match_all(cls, text, tags=None):
|
||||
|
||||
if tags is None:
|
||||
tags = cls.objects.all()
|
||||
|
||||
text = text.lower()
|
||||
for tag in tags:
|
||||
if tag.matches(text):
|
||||
yield tag
|
||||
|
||||
def matches(self, text):
|
||||
|
||||
search_kwargs = {}
|
||||
|
||||
# Check that match is not empty
|
||||
if self.match.strip() == "":
|
||||
return False
|
||||
|
||||
if self.is_insensitive:
|
||||
search_kwargs = {"flags": re.IGNORECASE}
|
||||
|
||||
if self.matching_algorithm == self.MATCH_ALL:
|
||||
for word in self._split_match():
|
||||
search_result = re.search(
|
||||
r"\b{}\b".format(word), text, **search_kwargs)
|
||||
if not search_result:
|
||||
return False
|
||||
return True
|
||||
|
||||
if self.matching_algorithm == self.MATCH_ANY:
|
||||
for word in self._split_match():
|
||||
if re.search(r"\b{}\b".format(word), text, **search_kwargs):
|
||||
return True
|
||||
return False
|
||||
|
||||
if self.matching_algorithm == self.MATCH_LITERAL:
|
||||
return bool(re.search(
|
||||
r"\b{}\b".format(self.match), text, **search_kwargs))
|
||||
|
||||
if self.matching_algorithm == self.MATCH_REGEX:
|
||||
return bool(re.search(
|
||||
re.compile(self.match, **search_kwargs), text))
|
||||
|
||||
if self.matching_algorithm == self.MATCH_FUZZY:
|
||||
match = re.sub(r'[^\w\s]', '', self.match)
|
||||
text = re.sub(r'[^\w\s]', '', text)
|
||||
if self.is_insensitive:
|
||||
match = match.lower()
|
||||
text = text.lower()
|
||||
|
||||
return True if fuzz.partial_ratio(match, text) >= 90 else False
|
||||
|
||||
raise NotImplementedError("Unsupported matching algorithm")
|
||||
|
||||
def _split_match(self):
|
||||
"""
|
||||
Splits the match to individual keywords, getting rid of unnecessary
|
||||
spaces and grouping quoted words together.
|
||||
|
||||
Example:
|
||||
' some random words "with quotes " and spaces'
|
||||
==>
|
||||
["some", "random", "words", "with+quotes", "and", "spaces"]
|
||||
"""
|
||||
findterms = re.compile(r'"([^"]+)"|(\S+)').findall
|
||||
normspace = re.compile(r"\s+").sub
|
||||
return [
|
||||
normspace(" ", (t[0] or t[1]).strip()).replace(" ", r"\s+")
|
||||
for t in findterms(self.match)
|
||||
]
|
||||
|
||||
def save(self, *args, **kwargs):
|
||||
|
||||
self.match = self.match.lower()
|
||||
self.slug = slugify(self.name)
|
||||
|
||||
models.Model.save(self, *args, **kwargs)
|
||||
@@ -183,6 +77,17 @@ class Tag(MatchingModel):
|
||||
|
||||
colour = models.PositiveIntegerField(choices=COLOURS, default=1)
|
||||
|
||||
is_inbox_tag = models.BooleanField(
|
||||
default=False,
|
||||
help_text="Marks this tag as an inbox tag: All newly consumed "
|
||||
"documents will be tagged with inbox tags."
|
||||
)
|
||||
|
||||
|
||||
class DocumentType(MatchingModel):
|
||||
|
||||
pass
|
||||
|
||||
|
||||
class Document(models.Model):
|
||||
|
||||
@@ -214,6 +119,14 @@ class Document(models.Model):
|
||||
|
||||
title = models.CharField(max_length=128, blank=True, db_index=True)
|
||||
|
||||
document_type = models.ForeignKey(
|
||||
DocumentType,
|
||||
blank=True,
|
||||
null=True,
|
||||
related_name="documents",
|
||||
on_delete=models.SET_NULL
|
||||
)
|
||||
|
||||
content = models.TextField(
|
||||
db_index=True,
|
||||
blank=True,
|
||||
@@ -254,6 +167,15 @@ class Document(models.Model):
|
||||
added = models.DateTimeField(
|
||||
default=timezone.now, editable=False, db_index=True)
|
||||
|
||||
archive_serial_number = models.IntegerField(
|
||||
blank=True,
|
||||
null=True,
|
||||
unique=True,
|
||||
db_index=True,
|
||||
help_text="The position of this document in your physical document "
|
||||
"archive."
|
||||
)
|
||||
|
||||
class Meta:
|
||||
ordering = ("correspondent", "title")
|
||||
|
||||
|
||||
@@ -1,20 +1,20 @@
|
||||
from rest_framework import serializers
|
||||
|
||||
from .models import Correspondent, Tag, Document, Log
|
||||
from .models import Correspondent, Tag, Document, Log, DocumentType
|
||||
|
||||
|
||||
class CorrespondentSerializer(serializers.HyperlinkedModelSerializer):
|
||||
|
||||
class Meta:
|
||||
model = Correspondent
|
||||
fields = (
|
||||
"id",
|
||||
"slug",
|
||||
"name",
|
||||
"match",
|
||||
"matching_algorithm",
|
||||
"is_insensitive"
|
||||
)
|
||||
fields = ("id", "slug", "name", "automatic_classification")
|
||||
|
||||
|
||||
class DocumentTypeSerializer(serializers.HyperlinkedModelSerializer):
|
||||
|
||||
class Meta:
|
||||
model = DocumentType
|
||||
fields = ("id", "slug", "name", "automatic_classification")
|
||||
|
||||
|
||||
class TagSerializer(serializers.HyperlinkedModelSerializer):
|
||||
@@ -22,14 +22,7 @@ class TagSerializer(serializers.HyperlinkedModelSerializer):
|
||||
class Meta:
|
||||
model = Tag
|
||||
fields = (
|
||||
"id",
|
||||
"slug",
|
||||
"name",
|
||||
"colour",
|
||||
"match",
|
||||
"matching_algorithm",
|
||||
"is_insensitive"
|
||||
)
|
||||
"id", "slug", "name", "colour", "automatic_classification")
|
||||
|
||||
|
||||
class CorrespondentField(serializers.HyperlinkedRelatedField):
|
||||
@@ -42,17 +35,25 @@ class TagsField(serializers.HyperlinkedRelatedField):
|
||||
return Tag.objects.all()
|
||||
|
||||
|
||||
class DocumentTypeField(serializers.HyperlinkedRelatedField):
|
||||
def get_queryset(self):
|
||||
return DocumentType.objects.all()
|
||||
|
||||
|
||||
class DocumentSerializer(serializers.ModelSerializer):
|
||||
|
||||
correspondent = CorrespondentField(
|
||||
view_name="drf:correspondent-detail", allow_null=True)
|
||||
tags = TagsField(view_name="drf:tag-detail", many=True)
|
||||
document_type = DocumentTypeField(
|
||||
view_name="drf:documenttype-detail", allow_null=True)
|
||||
|
||||
class Meta:
|
||||
model = Document
|
||||
fields = (
|
||||
"id",
|
||||
"correspondent",
|
||||
"document_type",
|
||||
"title",
|
||||
"content",
|
||||
"file_type",
|
||||
@@ -60,7 +61,6 @@ class DocumentSerializer(serializers.ModelSerializer):
|
||||
"checksum",
|
||||
"created",
|
||||
"modified",
|
||||
"added",
|
||||
"file_name",
|
||||
"download_url",
|
||||
"thumbnail_url",
|
||||
|
||||
59
src/documents/signals/handlers.py
Normal file → Executable file
59
src/documents/signals/handlers.py
Normal file → Executable file
@@ -8,57 +8,36 @@ from django.contrib.auth.models import User
|
||||
from django.contrib.contenttypes.models import ContentType
|
||||
from django.utils import timezone
|
||||
|
||||
from ..models import Correspondent, Document, Tag
|
||||
from documents.classifier import DocumentClassifier
|
||||
from ..models import Document, Tag
|
||||
|
||||
|
||||
def logger(message, group):
|
||||
logging.getLogger(__name__).debug(message, extra={"group": group})
|
||||
|
||||
|
||||
def set_correspondent(sender, document=None, logging_group=None, **kwargs):
|
||||
classifier = DocumentClassifier()
|
||||
|
||||
# No sense in assigning a correspondent when one is already set.
|
||||
if document.correspondent:
|
||||
return
|
||||
|
||||
# No matching correspondents, so no need to continue
|
||||
potential_correspondents = list(Correspondent.match_all(document.content))
|
||||
if not potential_correspondents:
|
||||
return
|
||||
|
||||
potential_count = len(potential_correspondents)
|
||||
selected = potential_correspondents[0]
|
||||
if potential_count > 1:
|
||||
message = "Detected {} potential correspondents, so we've opted for {}"
|
||||
logger(
|
||||
message.format(potential_count, selected),
|
||||
logging_group
|
||||
def classify_document(sender, document=None, logging_group=None, **kwargs):
|
||||
global classifier
|
||||
try:
|
||||
classifier.reload()
|
||||
classifier.classify_document(
|
||||
document,
|
||||
classify_correspondent=True,
|
||||
classify_tags=True,
|
||||
classify_document_type=True
|
||||
)
|
||||
except FileNotFoundError:
|
||||
logging.getLogger(__name__).fatal(
|
||||
"Cannot classify document, classifier model file was not found."
|
||||
)
|
||||
|
||||
logger(
|
||||
'Assigning correspondent "{}" to "{}" '.format(selected, document),
|
||||
logging_group
|
||||
)
|
||||
|
||||
document.correspondent = selected
|
||||
document.save(update_fields=("correspondent",))
|
||||
|
||||
|
||||
def set_tags(sender, document=None, logging_group=None, **kwargs):
|
||||
|
||||
current_tags = set(document.tags.all())
|
||||
relevant_tags = set(Tag.match_all(document.content)) - current_tags
|
||||
|
||||
if not relevant_tags:
|
||||
return
|
||||
|
||||
message = 'Tagging "{}" with "{}"'
|
||||
logger(
|
||||
message.format(document, ", ".join([t.slug for t in relevant_tags])),
|
||||
logging_group
|
||||
)
|
||||
|
||||
document.tags.add(*relevant_tags)
|
||||
def add_inbox_tags(sender, document=None, logging_group=None, **kwargs):
|
||||
inbox_tags = Tag.objects.filter(is_inbox_tag=True)
|
||||
document.tags.add(*inbox_tags)
|
||||
|
||||
|
||||
def run_pre_consume_script(sender, filename, **kwargs):
|
||||
|
||||
13922
src/documents/static/documents/js/pdf.js
Executable file
13922
src/documents/static/documents/js/pdf.js
Executable file
File diff suppressed because it is too large
Load Diff
1
src/documents/static/documents/js/pdf.js.map
Executable file
1
src/documents/static/documents/js/pdf.js.map
Executable file
File diff suppressed because one or more lines are too long
41660
src/documents/static/documents/js/pdf.worker.js
vendored
Executable file
41660
src/documents/static/documents/js/pdf.worker.js
vendored
Executable file
File diff suppressed because it is too large
Load Diff
1
src/documents/static/documents/js/pdf.worker.js.map
vendored
Executable file
1
src/documents/static/documents/js/pdf.worker.js.map
vendored
Executable file
File diff suppressed because one or more lines are too long
13
src/documents/static/paperless.css
Normal file → Executable file
13
src/documents/static/paperless.css
Normal file → Executable file
@@ -20,4 +20,17 @@ td a.tag {
|
||||
#result_list td textarea {
|
||||
width: 90%;
|
||||
height: 5em;
|
||||
}
|
||||
|
||||
#change_form_twocolumn_parent {
|
||||
display: flex;
|
||||
}
|
||||
#change_form_form_parent {
|
||||
flex:50%;
|
||||
margin-right: 10px;
|
||||
}
|
||||
#change_form_viewer_parent {
|
||||
flex:50%;
|
||||
margin-left: 10px;
|
||||
text-align: center;
|
||||
}
|
||||
@@ -3,63 +3,10 @@
|
||||
{# NOTE: This should probably be extending base.html. See CSS comment below details. #}
|
||||
|
||||
|
||||
{% load static %}
|
||||
{% load custom_css from customisation %}
|
||||
{% load custom_js from customisation %}
|
||||
|
||||
|
||||
{% block extrahead %}
|
||||
<link rel="icon" type="image/x-icon" href="{% url 'favicon' %}" />
|
||||
<style>
|
||||
#header {
|
||||
background-color: #90a9b7;
|
||||
line-height: inherit;
|
||||
height: auto;
|
||||
}
|
||||
#branding h1 {
|
||||
font-weight: inherit;
|
||||
font-size: inherit;
|
||||
}
|
||||
.button,
|
||||
.button:active,
|
||||
.button:focus,
|
||||
.button:hover,
|
||||
a.button,
|
||||
.submit-row input,
|
||||
input[type="submit"],
|
||||
input[type="submit"]:active,
|
||||
input[type="submit"]:focus,
|
||||
input[type="submit"]:hover,
|
||||
input[type="button"],
|
||||
input[type="button"]:active,
|
||||
input[type="button"]:focus,
|
||||
input[type="button"]:hover {
|
||||
background-color: #074f57;
|
||||
}
|
||||
.module h2,
|
||||
.module caption,
|
||||
.inline-group h2 {
|
||||
background-color: #90a9b7;
|
||||
}
|
||||
div.breadcrumbs {
|
||||
background-color: #077187;
|
||||
}
|
||||
.module h2,
|
||||
.module caption,
|
||||
.inline-group h2 {
|
||||
background-color: #077187;
|
||||
}
|
||||
</style>
|
||||
{% endblock %}
|
||||
|
||||
|
||||
{% block branding %}
|
||||
<h1 id="site-name">
|
||||
<a href="{% url 'admin:index' %}"><img src="{% static 'paperless/img/logo-light.png' %}" alt="Paperless" /></a>
|
||||
</h1>
|
||||
{% endblock %}
|
||||
|
||||
|
||||
{% block blockbots %}
|
||||
|
||||
{% comment %}
|
||||
|
||||
21
src/documents/templates/admin/documents/document/change_form.html
Normal file → Executable file
21
src/documents/templates/admin/documents/document/change_form.html
Normal file → Executable file
@@ -4,6 +4,27 @@
|
||||
|
||||
{{ block.super }}
|
||||
|
||||
{% if file_type in "pdf jpg png" %}
|
||||
|
||||
<div id="change_form_twocolumn_parent">
|
||||
<div id="change_form_form_parent"></div>
|
||||
<div id="change_form_viewer_parent">
|
||||
{% if file_type == "pdf" %}
|
||||
{% include "admin/documents/document/viewers/viewer_pdf.html" %}
|
||||
{% endif %}
|
||||
{% if file_type in "jpg png" %}
|
||||
{% include "admin/documents/document/viewers/viewer_image.html" %}
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script>
|
||||
django.jQuery("#change_form_form_parent").append(django.jQuery("#document_form"));
|
||||
django.jQuery("#content-main").append(django.jQuery("#change_form_twocolumn_parent"));
|
||||
</script>
|
||||
|
||||
{% endif %}
|
||||
|
||||
{% if next_object %}
|
||||
<script type="text/javascript">//<![CDATA[
|
||||
(function($){
|
||||
|
||||
29
src/documents/templates/admin/documents/document/change_list_results.html
Normal file → Executable file
29
src/documents/templates/admin/documents/document/change_list_results.html
Normal file → Executable file
@@ -24,11 +24,12 @@
|
||||
border: 1px solid #cccccc;
|
||||
border-radius: 2%;
|
||||
overflow: hidden;
|
||||
height: 300px;
|
||||
height: 350px;
|
||||
position: relative;
|
||||
}
|
||||
.result .header {
|
||||
padding: 5px;
|
||||
background-color: #90a9b7;
|
||||
background-color: #79AEC8;
|
||||
position: relative;
|
||||
}
|
||||
.result .header .checkbox {
|
||||
@@ -60,6 +61,11 @@
|
||||
.result a.tag {
|
||||
color: #ffffff;
|
||||
}
|
||||
.result .documentType {
|
||||
padding: 5px;
|
||||
background-color: #eeeeee;
|
||||
text-align: center;
|
||||
}
|
||||
.result .date {
|
||||
padding: 5px;
|
||||
}
|
||||
@@ -79,6 +85,15 @@
|
||||
.result .image img {
|
||||
width: 100%;
|
||||
}
|
||||
.result .footer {
|
||||
position: absolute;
|
||||
bottom: 0;
|
||||
right: 0;
|
||||
border-left: 1px solid #cccccc;
|
||||
border-top: 1px solid #cccccc;
|
||||
padding: 4px 10px 4px 10px;
|
||||
background: white;
|
||||
}
|
||||
|
||||
.grid {
|
||||
margin-right: 260px;
|
||||
@@ -152,7 +167,9 @@
|
||||
{# 4: Image #}
|
||||
{# 5: Correspondent #}
|
||||
{# 6: Tags #}
|
||||
{# 7: Document edit url #}
|
||||
{# 7: Archive serial number #}
|
||||
{# 8: Document type #}
|
||||
{# 9: Document edit url #}
|
||||
<div class="box">
|
||||
<div class="result">
|
||||
<div class="header">
|
||||
@@ -166,7 +183,7 @@
|
||||
selection would not be possible with mouse click + drag. Instead,
|
||||
the underlying link would be dragged.
|
||||
{% endcomment %}
|
||||
<div class="headerLink" onclick="location.href='{{ result.7 }}';"></div>
|
||||
<div class="headerLink" onclick="location.href='{{ result.9 }}';"></div>
|
||||
<div class="checkbox">{{ result.0 }}</div>
|
||||
<div class="info">
|
||||
{{ result.5 }}
|
||||
@@ -174,10 +191,14 @@
|
||||
{{ result.1 }}
|
||||
<div style="clear: both;"></div>
|
||||
</div>
|
||||
{% if '>-<' not in result.8 %}<div class="documentType">{{ result.8 }}</div>{% endif %}
|
||||
<div class="tags">{{ result.6 }}</div>
|
||||
<div class="date">{{ result.2 }}</div>
|
||||
<div style="clear: both;"></div>
|
||||
<div class="image">{{ result.4 }}</div>
|
||||
{# Only show the archive serial number if it is set on the document. #}
|
||||
{# checking for >-< (i.e., will a dash be displayed) doesn't feel like a very good solution to me. #}
|
||||
{% if '>-<' not in result.7 %}<div class="footer">#{{ result.7 }}</div>{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
{% endfor %}
|
||||
|
||||
0
src/documents/templates/admin/documents/document/select_object.html
Normal file → Executable file
0
src/documents/templates/admin/documents/document/select_object.html
Normal file → Executable file
@@ -0,0 +1 @@
|
||||
<img src="{{download_url}}" style="max-width: 100%">
|
||||
@@ -0,0 +1,130 @@
|
||||
{% load static %}
|
||||
|
||||
<div>
|
||||
<input id="prev" value="Previous" class="default" type="button">
|
||||
<input id="next" value="Next" class="default" type="button">
|
||||
|
||||
<span>Page: <span id="page_num"></span> / <span id="page_count"></span></span>
|
||||
|
||||
<input id="zoomin" value="+" class="default" type="button">
|
||||
<input id="zoomout" value="-" class="default" type="button">
|
||||
</div>
|
||||
|
||||
<div style="width: 100%; overflow: auto;">
|
||||
<canvas id="the-canvas"></canvas>
|
||||
</div>
|
||||
<script type="text/javascript" src="{% static 'documents/js/pdf.js' %}"></script>
|
||||
<script type="text/javascript" src="{% static 'documents/js/pdf.worker.js' %}"></script>
|
||||
|
||||
{# Load and display PDF document#}
|
||||
<script>
|
||||
var pdfjsLib = window['pdfjs-dist/build/pdf'];
|
||||
|
||||
var pdfDoc = null,
|
||||
pageNum = 1,
|
||||
pageRendering = false,
|
||||
pageNumPending = null,
|
||||
scale = 1.0,
|
||||
canvas = document.getElementById('the-canvas'),
|
||||
ctx = canvas.getContext('2d');
|
||||
|
||||
/**
|
||||
* Get page info from document, resize canvas accordingly, and render page.
|
||||
* @param num Page number.
|
||||
*/
|
||||
function renderPage(num) {
|
||||
pageRendering = true;
|
||||
// Using promise to fetch the page
|
||||
pdfDoc.getPage(num).then(function(page) {
|
||||
var viewport = page.getViewport(scale);
|
||||
canvas.height = viewport.height;
|
||||
canvas.width = viewport.width;
|
||||
// Render PDF page into canvas context
|
||||
var renderContext = {
|
||||
canvasContext: ctx,
|
||||
viewport: viewport
|
||||
};
|
||||
var renderTask = page.render(renderContext);
|
||||
// Wait for rendering to finish
|
||||
renderTask.promise.then(function () {
|
||||
pageRendering = false;
|
||||
if (pageNumPending !== null) {
|
||||
// New page rendering is pending
|
||||
renderPage(pageNumPending);
|
||||
pageNumPending = null;
|
||||
}
|
||||
});
|
||||
});
|
||||
// Update page counters
|
||||
document.getElementById('page_num').textContent = num;
|
||||
}
|
||||
|
||||
/**
|
||||
* If another page rendering in progress, waits until the rendering is
|
||||
* finised. Otherwise, executes rendering immediately.
|
||||
*/
|
||||
function queueRenderPage(num) {
|
||||
if (pageRendering) {
|
||||
pageNumPending = num;
|
||||
} else {
|
||||
renderPage(num);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Displays previous page.
|
||||
*/
|
||||
function onPrevPage() {
|
||||
if (pageNum <= 1) {
|
||||
return;
|
||||
}
|
||||
pageNum--;
|
||||
queueRenderPage(pageNum);
|
||||
}
|
||||
|
||||
document.getElementById('prev').addEventListener('click', onPrevPage);
|
||||
|
||||
/**
|
||||
* Displays next page.
|
||||
*/
|
||||
function onNextPage() {
|
||||
if (pageNum >= pdfDoc.numPages) {
|
||||
return;
|
||||
}
|
||||
pageNum++;
|
||||
queueRenderPage(pageNum);
|
||||
}
|
||||
|
||||
document.getElementById('next').addEventListener('click', onNextPage);
|
||||
|
||||
/**
|
||||
* Displays next page.
|
||||
*/
|
||||
function onZoomIn() {
|
||||
scale *= 1.2;
|
||||
queueRenderPage(pageNum);
|
||||
}
|
||||
|
||||
document.getElementById('zoomin').addEventListener('click', onZoomIn);
|
||||
|
||||
/**
|
||||
* Displays next page.
|
||||
*/
|
||||
function onZoomOut() {
|
||||
scale /= 1.2;
|
||||
queueRenderPage(pageNum);
|
||||
}
|
||||
|
||||
document.getElementById('zoomout').addEventListener('click', onZoomOut);
|
||||
|
||||
/**
|
||||
* Asynchronously downloads PDF.
|
||||
*/
|
||||
pdfjsLib.getDocument("{{download_url}}").then(function (pdfDoc_) {
|
||||
pdfDoc = pdfDoc_;
|
||||
document.getElementById('page_count').textContent = pdfDoc.numPages;
|
||||
// Initial/first page rendering
|
||||
renderPage(pageNum);
|
||||
});
|
||||
</script>
|
||||
|
||||
31
src/documents/views.py
Normal file → Executable file
31
src/documents/views.py
Normal file → Executable file
@@ -2,7 +2,6 @@ from django.http import HttpResponse, HttpResponseBadRequest
|
||||
from django.views.generic import DetailView, FormView, TemplateView
|
||||
from django_filters.rest_framework import DjangoFilterBackend
|
||||
from django.conf import settings
|
||||
from django.utils import cache
|
||||
|
||||
from paperless.db import GnuPG
|
||||
from paperless.mixins import SessionOrBasicAuthMixin
|
||||
@@ -21,14 +20,21 @@ from rest_framework.viewsets import (
|
||||
ReadOnlyModelViewSet
|
||||
)
|
||||
|
||||
from .filters import CorrespondentFilterSet, DocumentFilterSet, TagFilterSet
|
||||
from .filters import (
|
||||
CorrespondentFilterSet,
|
||||
DocumentFilterSet,
|
||||
TagFilterSet,
|
||||
DocumentTypeFilterSet
|
||||
)
|
||||
|
||||
from .forms import UploadForm
|
||||
from .models import Correspondent, Document, Log, Tag
|
||||
from .models import Correspondent, Document, Log, Tag, DocumentType
|
||||
from .serialisers import (
|
||||
CorrespondentSerializer,
|
||||
DocumentSerializer,
|
||||
LogSerializer,
|
||||
TagSerializer
|
||||
TagSerializer,
|
||||
DocumentTypeSerializer
|
||||
)
|
||||
|
||||
|
||||
@@ -57,12 +63,10 @@ class FetchView(SessionOrBasicAuthMixin, DetailView):
|
||||
}
|
||||
|
||||
if self.kwargs["kind"] == "thumb":
|
||||
response = HttpResponse(
|
||||
return HttpResponse(
|
||||
self._get_raw_data(self.object.thumbnail_file),
|
||||
content_type=content_types[Document.TYPE_PNG]
|
||||
)
|
||||
cache.patch_cache_control(response, max_age=31536000, private=True)
|
||||
return response
|
||||
|
||||
response = HttpResponse(
|
||||
self._get_raw_data(self.object.source_file),
|
||||
@@ -119,6 +123,17 @@ class TagViewSet(ModelViewSet):
|
||||
ordering_fields = ("name", "slug")
|
||||
|
||||
|
||||
class DocumentTypeViewSet(ModelViewSet):
|
||||
model = DocumentType
|
||||
queryset = DocumentType.objects.all()
|
||||
serializer_class = DocumentTypeSerializer
|
||||
pagination_class = StandardPagination
|
||||
permission_classes = (IsAuthenticated,)
|
||||
filter_backends = (DjangoFilterBackend, OrderingFilter)
|
||||
filter_class = DocumentTypeFilterSet
|
||||
ordering_fields = ("name", "slug")
|
||||
|
||||
|
||||
class DocumentViewSet(RetrieveModelMixin,
|
||||
UpdateModelMixin,
|
||||
DestroyModelMixin,
|
||||
@@ -133,7 +148,7 @@ class DocumentViewSet(RetrieveModelMixin,
|
||||
filter_class = DocumentFilterSet
|
||||
search_fields = ("title", "correspondent__name", "content")
|
||||
ordering_fields = (
|
||||
"id", "title", "correspondent__name", "created", "modified", "added")
|
||||
"id", "title", "correspondent__name", "created", "modified")
|
||||
|
||||
|
||||
class LogViewSet(ReadOnlyModelViewSet):
|
||||
|
||||
0
src/manage.py
Executable file → Normal file
0
src/manage.py
Executable file → Normal file
16
src/paperless/settings.py
Normal file → Executable file
16
src/paperless/settings.py
Normal file → Executable file
@@ -58,7 +58,7 @@ if _allowed_hosts:
|
||||
ALLOWED_HOSTS = _allowed_hosts.split(",")
|
||||
|
||||
FORCE_SCRIPT_NAME = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
|
||||
|
||||
|
||||
# Application definition
|
||||
|
||||
INSTALLED_APPS = [
|
||||
@@ -72,7 +72,6 @@ INSTALLED_APPS = [
|
||||
"corsheaders",
|
||||
"django_extensions",
|
||||
|
||||
"paperless",
|
||||
"documents.apps.DocumentsConfig",
|
||||
"reminders.apps.RemindersConfig",
|
||||
"paperless_tesseract.apps.PaperlessTesseractConfig",
|
||||
@@ -83,7 +82,6 @@ INSTALLED_APPS = [
|
||||
"rest_framework",
|
||||
"crispy_forms",
|
||||
"django_filters",
|
||||
"djangoql",
|
||||
|
||||
]
|
||||
|
||||
@@ -146,9 +144,9 @@ DATABASES = {
|
||||
}
|
||||
}
|
||||
|
||||
if os.getenv("PAPERLESS_DBUSER"):
|
||||
if os.getenv("PAPERLESS_DBENGINE"):
|
||||
DATABASES["default"] = {
|
||||
"ENGINE": "django.db.backends.postgresql_psycopg2",
|
||||
"ENGINE": os.getenv("PAPERLESS_DBENGINE"),
|
||||
"NAME": os.getenv("PAPERLESS_DBNAME", "paperless"),
|
||||
"USER": os.getenv("PAPERLESS_DBUSER"),
|
||||
}
|
||||
@@ -215,6 +213,14 @@ MEDIA_URL = os.getenv("PAPERLESS_MEDIA_URL", "/media/")
|
||||
DATA_UPLOAD_MAX_NUMBER_FIELDS = None
|
||||
|
||||
|
||||
# Document classification models location
|
||||
MODEL_FILE = os.getenv(
|
||||
"PAPERLESS_MODEL_FILE", os.path.join(
|
||||
BASE_DIR, "..", "models", "model.pickle"
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
# Paperless-specific stuff
|
||||
# You shouldn't have to edit any of these values. Rather, you can set these
|
||||
# values in /etc/paperless.conf instead.
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 108 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 6.2 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 8.6 KiB |
8
src/paperless/urls.py
Normal file → Executable file
8
src/paperless/urls.py
Normal file → Executable file
@@ -6,19 +6,20 @@ from django.views.decorators.csrf import csrf_exempt
|
||||
from django.views.generic import RedirectView
|
||||
from rest_framework.routers import DefaultRouter
|
||||
|
||||
from paperless.views import FaviconView
|
||||
from documents.views import (
|
||||
CorrespondentViewSet,
|
||||
DocumentViewSet,
|
||||
FetchView,
|
||||
LogViewSet,
|
||||
PushView,
|
||||
TagViewSet
|
||||
TagViewSet,
|
||||
DocumentTypeViewSet
|
||||
)
|
||||
from reminders.views import ReminderViewSet
|
||||
|
||||
router = DefaultRouter()
|
||||
router.register(r"correspondents", CorrespondentViewSet)
|
||||
router.register(r"document_types", DocumentTypeViewSet)
|
||||
router.register(r"documents", DocumentViewSet)
|
||||
router.register(r"logs", LogViewSet)
|
||||
router.register(r"reminders", ReminderViewSet)
|
||||
@@ -45,9 +46,6 @@ urlpatterns = [
|
||||
# File uploads
|
||||
url(r"^push$", csrf_exempt(PushView.as_view()), name="push"),
|
||||
|
||||
# Favicon
|
||||
url(r"^favicon.ico$", FaviconView.as_view(), name="favicon"),
|
||||
|
||||
# The Django admin
|
||||
url(r"admin/", admin.site.urls),
|
||||
|
||||
|
||||
@@ -1 +1 @@
|
||||
__version__ = (2, 6, 1)
|
||||
__version__ = (1, 0, 1)
|
||||
|
||||
@@ -1,7 +1,3 @@
|
||||
import os
|
||||
|
||||
from django.http import HttpResponse
|
||||
from django.views.generic import View
|
||||
from rest_framework.pagination import PageNumberPagination
|
||||
|
||||
|
||||
@@ -9,17 +5,3 @@ class StandardPagination(PageNumberPagination):
|
||||
page_size = 25
|
||||
page_size_query_param = "page-size"
|
||||
max_page_size = 100000
|
||||
|
||||
|
||||
class FaviconView(View):
|
||||
|
||||
def get(self, request, *args, **kwargs):
|
||||
favicon = os.path.join(
|
||||
os.path.dirname(__file__),
|
||||
"static",
|
||||
"paperless",
|
||||
"img",
|
||||
"favicon.ico"
|
||||
)
|
||||
with open(favicon, "rb") as f:
|
||||
return HttpResponse(f, content_type="image/x-icon")
|
||||
|
||||
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 136 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_1.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_1.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_1.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_1.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 136 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_2.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_2.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_2.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_2.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 135 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_3.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_3.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_3.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_3.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 46 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_4.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_4.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_4.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_4.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 53 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_5.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_5.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_5.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_5.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 136 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_6.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_6.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_6.png
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_6.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 136 KiB |
BIN
src/paperless_tesseract/tests/samples/tests_date_7.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_7.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_8.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_8.pdf
Normal file
Binary file not shown.
BIN
src/paperless_tesseract/tests/samples/tests_date_9.pdf
Normal file
BIN
src/paperless_tesseract/tests/samples/tests_date_9.pdf
Normal file
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 136 KiB |
@@ -5,7 +5,7 @@ from unittest import mock
|
||||
from uuid import uuid4
|
||||
|
||||
from dateutil import tz
|
||||
from django.test import TestCase
|
||||
from django.test import TestCase, override_settings
|
||||
|
||||
from ..parsers import RasterisedDocumentParser
|
||||
from django.conf import settings
|
||||
@@ -16,36 +16,46 @@ class TestDate(TestCase):
|
||||
SAMPLE_FILES = os.path.join(os.path.dirname(__file__), "samples")
|
||||
SCRATCH = "/tmp/paperless-tests-{}".format(str(uuid4())[:8])
|
||||
|
||||
MOCK_SCRATCH = "paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH" # NOQA: E501
|
||||
|
||||
def setUp(self):
|
||||
os.makedirs(self.SCRATCH, exist_ok=True)
|
||||
|
||||
def tearDown(self):
|
||||
shutil.rmtree(self.SCRATCH)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_1(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document._text = "lorem ipsum 130218 lorem ipsum"
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_2(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document._text = "lorem ipsum 2018 lorem ipsum"
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_3(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document._text = "lorem ipsum 20180213 lorem ipsum"
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_4(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -59,7 +69,10 @@ class TestDate(TestCase):
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_5(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -76,7 +89,10 @@ class TestDate(TestCase):
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_6(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -93,7 +109,10 @@ class TestDate(TestCase):
|
||||
)
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_7(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -111,7 +130,10 @@ class TestDate(TestCase):
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_8(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -135,7 +157,10 @@ class TestDate(TestCase):
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_date_format_9(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
@@ -153,11 +178,398 @@ class TestDate(TestCase):
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_1_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_1.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
date = document.get_date()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
date,
|
||||
datetime.datetime(
|
||||
2018, 4, 1, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_1_png(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_1.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 4, 1, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_2_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_2.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2013, 2, 1, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_2_png(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_2.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2013, 2, 1, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
@override_settings(OCR_LANGUAGE="deu")
|
||||
def test_get_text_3_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_3.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 10, 5, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
@override_settings(OCR_LANGUAGE="deu")
|
||||
def test_get_text_3_png(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_3.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 10, 5, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
@override_settings(OCR_LANGUAGE="eng")
|
||||
def test_get_text_4_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_4.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 10, 5, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
@override_settings(OCR_LANGUAGE="eng")
|
||||
def test_get_text_4_png(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_4.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 10, 5, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_5_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_5.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 12, 17, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_5_png(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_5.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 12, 17, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_6_pdf_us(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_6.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.get_text()
|
||||
document.DATE_ORDER = "MDY"
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 12, 17, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_6_png_us(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_6.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.get_text()
|
||||
document.DATE_ORDER = "MDY"
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 12, 17, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_6_pdf_eu(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_6.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_6_png_eu(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_6.png")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(document.get_date(), None)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_7_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_7.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2018, 4, 1, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_8_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_8.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2017, 12, 31, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_get_text_9_pdf(self):
|
||||
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_9.pdf")
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.DATE_ORDER = 'DMY'
|
||||
document.get_text()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
document.get_date(),
|
||||
datetime.datetime(
|
||||
2017, 12, 31, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_filename_date_1_pdf(self):
|
||||
input_file = os.path.join(
|
||||
self.SAMPLE_FILES,
|
||||
"tests_date_in_filename_2018-03-20_1.pdf"
|
||||
)
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.FILENAME_DATE_ORDER = 'YMD'
|
||||
document.get_text()
|
||||
date = document.get_date()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
date,
|
||||
datetime.datetime(
|
||||
2018, 3, 20, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_filename_date_1_png(self):
|
||||
input_file = os.path.join(
|
||||
self.SAMPLE_FILES,
|
||||
"tests_date_in_filename_2018-03-20_1.png"
|
||||
)
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.FILENAME_DATE_ORDER = 'YMD'
|
||||
date = document.get_date()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
date,
|
||||
datetime.datetime(
|
||||
2018, 3, 20, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_filename_date_2_pdf(self):
|
||||
input_file = os.path.join(
|
||||
self.SAMPLE_FILES,
|
||||
"2013-12-11_tests_date_in_filename_2.pdf"
|
||||
)
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.FILENAME_DATE_ORDER = 'YMD'
|
||||
date = document.get_date()
|
||||
self.assertEqual(document._is_ocred(), True)
|
||||
self.assertEqual(
|
||||
date,
|
||||
datetime.datetime(
|
||||
2013, 12, 11, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_filename_date_2_png(self):
|
||||
input_file = os.path.join(
|
||||
self.SAMPLE_FILES,
|
||||
"2013-12-11_tests_date_in_filename_2.png"
|
||||
)
|
||||
document = RasterisedDocumentParser(input_file)
|
||||
document.FILENAME_DATE_ORDER = 'YMD'
|
||||
date = document.get_date()
|
||||
self.assertEqual(document._is_ocred(), False)
|
||||
self.assertEqual(
|
||||
date,
|
||||
datetime.datetime(
|
||||
2013, 12, 11, 0, 0,
|
||||
tzinfo=tz.gettz(settings.TIME_ZONE)
|
||||
)
|
||||
)
|
||||
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
|
||||
return_value="01-07-0590 00:00:00"
|
||||
)
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_crazy_date_past(self, *args):
|
||||
document = RasterisedDocumentParser("/dev/null")
|
||||
document.get_text()
|
||||
@@ -167,7 +579,10 @@ class TestDate(TestCase):
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
|
||||
return_value="01-07-2350 00:00:00"
|
||||
)
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_crazy_date_future(self, *args):
|
||||
document = RasterisedDocumentParser("/dev/null")
|
||||
document.get_text()
|
||||
@@ -177,7 +592,10 @@ class TestDate(TestCase):
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
|
||||
return_value="01-07-0590 00:00:00"
|
||||
)
|
||||
@mock.patch(MOCK_SCRATCH, SCRATCH)
|
||||
@mock.patch(
|
||||
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
|
||||
SCRATCH
|
||||
)
|
||||
def test_crazy_date_past(self, *args):
|
||||
document = RasterisedDocumentParser("/dev/null")
|
||||
document.get_text()
|
||||
|
||||
@@ -17,5 +17,6 @@ deps=pycodestyle
|
||||
|
||||
[testenv:doc]
|
||||
deps =
|
||||
-r {toxinidir}/../requirements.txt
|
||||
-r{toxinidir}/../requirements.txt
|
||||
sphinx
|
||||
commands=sphinx-build -b html ../docs ../docs/_build -W
|
||||
|
||||
Reference in New Issue
Block a user