mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-10-30 03:56:23 -05:00
add prototype archive pdf
This commit is contained in:
phail
46
src/paperless_mail/mail_template/index.html
Normal file
46
src/paperless_mail/mail_template/index.html
Normal file
@@ -0,0 +1,46 @@
|
||||
<!doctype html>
|
||||
<html>
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<link href="output.css" rel="stylesheet">
|
||||
</head>
|
||||
|
||||
<body class="bg-white w-screen flex flex-col items-center">
|
||||
<div class="container max-w-4xl">
|
||||
<!-- Header -->
|
||||
<div class="grid grid-rows-5 grid-cols-12 gap-x-2 bg-slate-200 p-4">
|
||||
|
||||
<div class="col-start-11 col-span-2 row-start-1 text-right">23.04.2022 18:18</div>
|
||||
|
||||
<div class="col-start-1 row-start-1 text-slate-400 text-right">From</div>
|
||||
<div class="col-start-2 col-span-8 row-start 1">{{ from }}</div>
|
||||
|
||||
<div class="col-start-1 row-start-2 text-slate-400 text-right">Subject</div>
|
||||
<div class=" col-start-2 col-span-10 row-start 2 font-bold">{{ Subject }}
|
||||
</div>
|
||||
|
||||
<div class="col-start-1 row-start-3 text-slate-400 text-right">To</div>
|
||||
<div class="col-start-2 col-span-10 row-start 3">{{ To }}
|
||||
</div>
|
||||
|
||||
<div class="col-start-1 row-start-4 text-slate-400 text-right">CC</div>
|
||||
<div class="col-start-2 col-span-10 row-start 4">{{ CC }}
|
||||
</div>
|
||||
|
||||
<div class="col-start-1 row-start-5 text-slate-400 text-right">BCC</div>
|
||||
<div class="col-start-2 col-span-10 row-start 5">{{ BCC }}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Separator-->
|
||||
<div class="border-t border-solid border-b w-full h-[1px] box-content border-black mb-5 bg-slate-200"></div>
|
||||
|
||||
<!-- Content-->
|
||||
<div class="w-full whitespace-pre-line">{{ content }}
|
||||
</div>
|
||||
|
||||
</body>
|
||||
|
||||
</html>
|
||||
0
src/paperless_mail/mail_template/output.css
Normal file
0
src/paperless_mail/mail_template/output.css
Normal file
@@ -8,9 +8,6 @@ from django.conf import settings
|
||||
from documents.parsers import DocumentParser
|
||||
from documents.parsers import make_thumbnail_from_pdf
|
||||
from documents.parsers import ParseError
|
||||
from PIL import Image
|
||||
from PIL import ImageDraw
|
||||
from PIL import ImageFont
|
||||
from tika import parser
|
||||
|
||||
|
||||
@@ -112,22 +109,19 @@ class TikaDocumentParserEml(DocumentParser):
|
||||
logging_name = "paperless.parsing.tikaeml"
|
||||
|
||||
def get_thumbnail(self, document_path, mime_type, file_name=None):
|
||||
if not self.archive_path:
|
||||
self.archive_path = self.generate_pdf(document_path)
|
||||
|
||||
img = Image.new("RGB", (500, 700), color="white")
|
||||
draw = ImageDraw.Draw(img)
|
||||
font = ImageFont.truetype(
|
||||
font=settings.THUMBNAIL_FONT_NAME,
|
||||
size=20,
|
||||
layout_engine=ImageFont.LAYOUT_BASIC,
|
||||
return make_thumbnail_from_pdf(
|
||||
self.archive_path,
|
||||
self.tempdir,
|
||||
self.logging_group,
|
||||
)
|
||||
draw.text((5, 5), self.text, font=font, fill="black")
|
||||
|
||||
out_path = os.path.join(self.tempdir, "thumb.png")
|
||||
img.save(out_path)
|
||||
|
||||
return out_path
|
||||
|
||||
def extract_metadata(self, document_path, mime_type):
|
||||
result = []
|
||||
prefix_pattern = re.compile(r"(.*):(.*)")
|
||||
|
||||
tika_server = settings.PAPERLESS_TIKA_ENDPOINT
|
||||
try:
|
||||
parsed = parser.from_file(document_path, tika_server)
|
||||
@@ -136,17 +130,38 @@ class TikaDocumentParserEml(DocumentParser):
|
||||
"warning",
|
||||
f"Error while fetching document metadata for " f"{document_path}: {e}",
|
||||
)
|
||||
return []
|
||||
return result
|
||||
|
||||
return [
|
||||
for key, value in parsed["metadata"].items():
|
||||
if isinstance(value, list):
|
||||
value = ", ".join([str(e) for e in value])
|
||||
value = str(value)
|
||||
try:
|
||||
m = prefix_pattern.match(key)
|
||||
result.append(
|
||||
{
|
||||
"namespace": "",
|
||||
"prefix": m.group(1),
|
||||
"key": m.group(2),
|
||||
"value": value,
|
||||
},
|
||||
)
|
||||
except AttributeError:
|
||||
result.append(
|
||||
{
|
||||
"namespace": "",
|
||||
"prefix": "",
|
||||
"key": key,
|
||||
"value": parsed["metadata"][key],
|
||||
}
|
||||
for key in parsed["metadata"]
|
||||
]
|
||||
"value": value,
|
||||
},
|
||||
)
|
||||
except Exception as e:
|
||||
self.log(
|
||||
"warning",
|
||||
f"Error while reading metadata {key}: {value}. Error: " f"{e}",
|
||||
)
|
||||
result.sort(key=lambda item: (item["prefix"], item["key"]))
|
||||
return result
|
||||
|
||||
def parse(self, document_path, mime_type, file_name=None):
|
||||
self.log("info", f"Sending {document_path} to Tika server")
|
||||
@@ -160,31 +175,75 @@ class TikaDocumentParserEml(DocumentParser):
|
||||
f"{tika_server}: {err}",
|
||||
)
|
||||
|
||||
text = re.sub(" +", " ", str(parsed))
|
||||
text = re.sub("\n+", "\n", text)
|
||||
self.text = text
|
||||
metadata = parsed["metadata"].copy()
|
||||
|
||||
print(text)
|
||||
subject = metadata.pop("dc:subject", "<no subject>")
|
||||
content = parsed["content"].strip()
|
||||
|
||||
if content.startswith(subject):
|
||||
content = content[len(subject) :].strip()
|
||||
|
||||
content = re.sub(" +", " ", content)
|
||||
content = re.sub("\n+", "\n", content)
|
||||
|
||||
self.text = (
|
||||
f"{content}\n"
|
||||
f"______________________\n"
|
||||
f"From: {metadata.pop('Message-From', '')}\n"
|
||||
f"To: {metadata.pop('Message-To', '')}\n"
|
||||
f"CC: {metadata.pop('Message-CC', '')}"
|
||||
)
|
||||
|
||||
try:
|
||||
self.date = dateutil.parser.isoparse(parsed["metadata"]["Creation-Date"])
|
||||
self.date = dateutil.parser.isoparse(parsed["metadata"]["dcterms:created"])
|
||||
except Exception as e:
|
||||
self.log(
|
||||
"warning",
|
||||
f"Unable to extract date for document " f"{document_path}: {e}",
|
||||
)
|
||||
|
||||
md_path = self.convert_to_md(document_path, file_name)
|
||||
self.archive_path = self.convert_md_to_pdf(md_path)
|
||||
self.archive_path = self.generate_pdf(document_path, parsed)
|
||||
|
||||
def generate_pdf(self, document_path, parsed=None):
|
||||
if not parsed:
|
||||
self.log("info", f"Sending {document_path} to Tika server")
|
||||
tika_server = settings.PAPERLESS_TIKA_ENDPOINT
|
||||
|
||||
try:
|
||||
parsed = parser.from_file(document_path, tika_server)
|
||||
except Exception as err:
|
||||
raise ParseError(
|
||||
f"Could not parse {document_path} with tika server at "
|
||||
f"{tika_server}: {err}",
|
||||
)
|
||||
|
||||
def clean_html(text: str):
|
||||
if isinstance(text, list):
|
||||
text = ", ".join([str(e) for e in text])
|
||||
if type(text) != str:
|
||||
text = str(text)
|
||||
text = text.replace("&", "&")
|
||||
text = text.replace("<", "<")
|
||||
text = text.replace(">", ">")
|
||||
text = text.replace(" ", " ")
|
||||
text = text.replace("'", "'")
|
||||
text = text.replace('"', """)
|
||||
return text
|
||||
|
||||
def convert_md_to_pdf(self, md_path):
|
||||
pdf_path = os.path.join(self.tempdir, "convert.pdf")
|
||||
gotenberg_server = settings.PAPERLESS_TIKA_GOTENBERG_ENDPOINT
|
||||
url = gotenberg_server + "/forms/chromium/convert/markdown"
|
||||
url = gotenberg_server + "/forms/chromium/convert/html"
|
||||
|
||||
self.log("info", f"Converting {document_path} to PDF as {pdf_path}")
|
||||
|
||||
subject = parsed["metadata"].pop("dc:subject", "<no subject>")
|
||||
content = parsed.pop("content", "<no content>").strip()
|
||||
|
||||
if content.startswith(subject):
|
||||
content = content[len(subject) :].strip()
|
||||
|
||||
self.log("info", f"Converting {md_path} to PDF as {pdf_path}")
|
||||
html = StringIO(
|
||||
"""
|
||||
f"""
|
||||
<!doctype html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
@@ -192,25 +251,18 @@ class TikaDocumentParserEml(DocumentParser):
|
||||
<title>My PDF</title>
|
||||
</head>
|
||||
<body>
|
||||
{{ toHTML "convert.md" }}
|
||||
<h1>{clean_html(subject)}</h1>
|
||||
<p>From: {clean_html(parsed['metadata'].pop('Message-From', ''))}
|
||||
<p>To: {clean_html(parsed['metadata'].pop('Message-To', ''))}
|
||||
<p>CC: {clean_html(parsed['metadata'].pop('Message-CC', ''))}
|
||||
<p>Date: {clean_html(parsed['metadata'].pop('dcterms:created', ''))}
|
||||
<pre>{clean_html(content)}</pre>
|
||||
</body>
|
||||
</html>
|
||||
""",
|
||||
)
|
||||
md = StringIO(
|
||||
"""
|
||||
# Subject
|
||||
|
||||
blub \nblah
|
||||
blib
|
||||
""",
|
||||
)
|
||||
|
||||
files = {
|
||||
"md": (
|
||||
os.path.basename(md_path),
|
||||
md,
|
||||
),
|
||||
"html": (
|
||||
"index.html",
|
||||
html,
|
||||
@@ -229,19 +281,3 @@ blib
|
||||
file.close()
|
||||
|
||||
return pdf_path
|
||||
|
||||
def convert_to_md(self, document_path, file_name):
|
||||
md_path = os.path.join(self.tempdir, "convert.md")
|
||||
|
||||
self.log("info", f"Converting {document_path} to markdown as {md_path}")
|
||||
|
||||
with open(md_path, "w") as file:
|
||||
md = [
|
||||
"# Subject",
|
||||
"\n\n",
|
||||
"blah",
|
||||
]
|
||||
file.writelines(md)
|
||||
file.close()
|
||||
|
||||
return md_path
|
||||
|
||||
Reference in New Issue
Block a user