paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-29 11:09:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

add parsing of inline attachments

Browse Source 
remove insecure chromium option
fix html parsing
This commit is contained in:
phail 2022-05-03 23:21:33 +02:00
parent 5a899664f8
commit c2e3dc76d9
7 changed files with 95 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docker/compose/docker-compose.postgres-tika.yml
View File

@ -79,9 +79,6 @@ services:
gotenberg:
image: gotenberg/gotenberg:7.4
restart: unless-stopped
command:
- "gotenberg"
- "--chromium-disable-web-security"
tika:
image: ghcr.io/paperless-ngx/tika:latest

3
docker/compose/docker-compose.sqlite-tika.yml
View File

@ -67,9 +67,6 @@ services:
gotenberg:
image: gotenberg/gotenberg:7.4
restart: unless-stopped
command:
- "gotenberg"
- "--chromium-disable-web-security"
tika:
image: ghcr.io/paperless-ngx/tika:latest

3
docs/configuration.rst
View File

@ -497,9 +497,6 @@ requires are as follows:
gotenberg:
image: gotenberg/gotenberg:7.4
restart: unless-stopped
command:
- "gotenberg"
- "--chromium-disable-web-security"
tika:
image: ghcr.io/paperless-ngx/tika:latest

1
docs/troubleshooting.rst
View File

@ -129,7 +129,6 @@ If using docker-compose, this is achieved by the following configuration change
restart: unless-stopped
command:
- "gotenberg"
- "--chromium-disable-web-security"
- "--api-timeout=60"
Permission denied errors in the consumption directory

2
scripts/start_services.sh
View File

@ -2,5 +2,5 @@
docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
docker run -d -p 6379:6379 redis:latest
docker run -p 3000:3000 -d gotenberg/gotenberg:7.4 gotenberg --chromium-disable-web-security
docker run -p 3000:3000 -d gotenberg/gotenberg:7.4
docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest

13
src/paperless_mail/mail_template/index.html
View File

@ -37,20 +37,9 @@
<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 break-words">{{ content }} </div>
<div class="border-t border-solid border-b w-full h-[1px] box-content border-black mb-5 bg-slate-200"></div>
<iframe src=mail_html.html style="width: 100%;" scrolling="no" id="myIframe" ></iframe>
<div class="w-full break-words">{{ content }}</div>
</div>
<script>
// Selecting the iframe element
var iframe = document.getElementById("myIframe");
// Adjusting the iframe height onload event
iframe.onload = function(){
iframe.style.height = iframe.contentWindow.document.body.scrollHeight + 'px';
}
</script>
</body>
</html>

133
src/paperless_mail/parsers.py
View File

@ -1,5 +1,6 @@
import os
import re
from io import BytesIO
from io import StringIO
import requests
@ -92,61 +93,50 @@ class MailDocumentParser(DocumentParser):
return result
def parse(self, document_path, mime_type, file_name=None):
def strip_content(text: str):
text = re.sub("\t", " ", text)
text = re.sub(" +", " ", text)
text = re.sub("(\n *)+", "\n", text)
return text.strip()
mail = self.get_parsed(document_path)
content = mail.text.strip()
content = re.sub(" +", " ", content)
content = re.sub("\n+", "\n", content)
self.text = f"{content}\n\n"
self.text += f"Subject: {mail.subject}\n"
self.text += f"From: {mail.from_values.full}\n"
self.text += f"To: {', '.join(address.full for address in mail.to_values)}\n"
self.text = f"{strip_content(mail.text)}\n\n"
self.text += f"Subject: {mail.subject}\n\n"
self.text += f"From: {mail.from_values.full}\n\n"
self.text += f"To: {', '.join(address.full for address in mail.to_values)}\n\n"
if len(mail.cc_values) >= 1:
self.text += (
f"CC: {', '.join(address.full for address in mail.cc_values)}\n"
f"CC: {', '.join(address.full for address in mail.cc_values)}\n\n"
)
if len(mail.bcc_values) >= 1:
self.text += (
f"BCC: {', '.join(address.full for address in mail.bcc_values)}\n"
f"BCC: {', '.join(address.full for address in mail.bcc_values)}\n\n"
)
if len(mail.attachments) >= 1:
att = ", ".join(f"{a.filename} ({a.size})" for a in mail.attachments)
self.text += f"Attachments: {att}"
self.text += f"Attachments: {att}\n\n"
if mail.html != "":
self.text += "HTML content: " + strip_content(self.tika_parse(mail.html))
self.date = mail.date
self.archive_path = self.generate_pdf(document_path)
def tika_parse(self, document_path):
self.log("info", f"Sending {document_path} to Tika server")
def tika_parse(self, input):
self.log("info", "Sending content to Tika server")
tika_server = settings.PAPERLESS_TIKA_ENDPOINT
try:
parsed = parser.from_file(document_path, tika_server)
parsed = parser.from_buffer(input, tika_server)
except Exception as err:
raise ParseError(
f"Could not parse {document_path} with tika server at "
f"{tika_server}: {err}",
f"Could not parse content with tika server at " f"{tika_server}: {err}",
)
subject = parsed["metadata"].get("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)
text = (
f"{content}\n\n"
f"From: {parsed['metadata'].get('Message-From', '')}\n"
f"To: {parsed['metadata'].get('Message-To', '')}\n"
f"CC: {parsed['metadata'].get('Message-CC', '')}"
)
return text
if parsed["content"]:
return parsed["content"]
else:
return ""
def generate_pdf(self, document_path):
def clean_html(text: str):
@ -201,7 +191,6 @@ class MailDocumentParser(DocumentParser):
css_file = os.path.join(os.path.dirname(__file__), "mail_template/output.css")
placeholder_pattern = re.compile(r"{{(.+)}}")
html = StringIO()
orig_html = StringIO(clean_html_script(mail.html))
with open(html_file, "r") as html_template_handle:
with open(css_file, "rb") as css_handle:
@ -223,10 +212,6 @@ class MailDocumentParser(DocumentParser):
"output.css",
css_handle,
),
"mail_html": (
"mail_html.html",
orig_html,
),
}
headers = {}
data = {
@ -249,8 +234,76 @@ class MailDocumentParser(DocumentParser):
except Exception as err:
raise ParseError(f"Error while converting document to PDF: {err}")
if mail.html != "":
pdf_html = self.generate_pdf_from_html(
clean_html_script(mail.html),
mail.attachments,
)
url_merge = gotenberg_server + "/forms/pdfengines/merge"
files = {
"mail": (
"1_mail.pdf",
BytesIO(response.content),
),
"html": (
"2_html.pdf",
BytesIO(pdf_html),
),
}
headers = {}
try:
response = requests.post(
url_merge,
files=files,
headers=headers,
)
response.raise_for_status() # ensure we notice bad responses
except Exception as err:
raise ParseError(f"Error while converting document to PDF: {err}")
with open(pdf_path, "wb") as file:
file.write(response.content)
file.close()
return pdf_path
def generate_pdf_from_html(self, orig_html, attachments):
gotenberg_server = settings.PAPERLESS_TIKA_GOTENBERG_ENDPOINT
url = gotenberg_server + "/forms/chromium/convert/html"
self.log("info", "Converting html to PDF")
files = {}
for a in attachments:
name_cid = "cid:" + a.content_id
name_clean = "".join(e for e in name_cid if e.isalnum())
files[name_clean] = (name_clean, BytesIO(a.payload))
orig_html = orig_html.replace(name_cid, name_clean)
files["mail_html"] = ("index.html", StringIO(orig_html))
headers = {}
data = {
"marginTop": "0.1",
"marginBottom": "0.1",
"marginLeft": "0.1",
"marginRight": "0.1",
"paperWidth": "8.27",
"paperHeight": "11.7",
"scale": "1.0",
}
try:
response = requests.post(
url,
files=files,
headers=headers,
data=data,
)
response.raise_for_status() # ensure we notice bad responses
except Exception as err:
raise ParseError(f"Error while converting document to PDF: {err}")
return response.content