mirror of https://github.com/papermerge/mglib
Merge pull request #6 from francescocarzaniga/master
Replace extension checking with python-magicmaster
commit
8d5077933f
|
@ -24,7 +24,7 @@ jobs:
|
|||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pycodestyle pytest coverage
|
||||
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
|
||||
if [ -f requirements/base.txt ]; then pip install -r requirements/base.txt; fi
|
||||
sudo apt install poppler-utils pdftk
|
||||
- name: Lint with pycodestyle
|
||||
run: |
|
||||
|
|
|
@ -2,6 +2,7 @@ import os
|
|||
import re
|
||||
import subprocess
|
||||
import logging
|
||||
from magic import from_file
|
||||
|
||||
from .conf import settings
|
||||
from .exceptions import FileTypeNotSupported
|
||||
|
@ -63,18 +64,18 @@ def get_pagecount(filepath):
|
|||
if os.path.isdir(filepath):
|
||||
raise ValueError("Filepath %s is a directory!" % filepath)
|
||||
|
||||
base, ext = os.path.splitext(filepath)
|
||||
mime_type = from_file(filepath, mime=True)
|
||||
|
||||
# pure images (png, jpeg) have only one page :)
|
||||
if ext and ext.lower() in ('.jpeg', '.png', '.jpg'):
|
||||
if mime_type in ['image/png', 'image/jpeg', 'image/jpg']:
|
||||
# whatever png/jpg image is there - it is
|
||||
# considered by default one page document.
|
||||
return 1
|
||||
|
||||
if ext and ext.lower() in ('.tiff', ):
|
||||
if mime_type == 'image/tiff':
|
||||
return get_tiff_pagecount(filepath)
|
||||
|
||||
if ext and ext.lower() not in ('.pdf', '.tiff'):
|
||||
if mime_type != 'application/pdf':
|
||||
raise FileTypeNotSupported(
|
||||
"Only jpeg, png, pdf and tiff are handled by this"
|
||||
" method"
|
||||
|
|
|
@ -0,0 +1 @@
|
|||
python-magic
|
|
@ -1,2 +1,2 @@
|
|||
I am not even binary!
|
||||
ÿØÿØI am not even binary!
|
||||
The idea is to test pdfinfo.get_pagecount
|
Before Width: | Height: | Size: 63 B After Width: | Height: | Size: 67 B |
|
@ -1 +1 @@
|
|||
well... I am text! But who cares? The idea is to test pdfinfo.get_pagecount
|
||||
ÿØÿîwell... I am text! But who cares? The idea is to test pdfinfo.get_pagecount
|
Before Width: | Height: | Size: 75 B After Width: | Height: | Size: 79 B |
Binary file not shown.
Before Width: | Height: | Size: 75 B After Width: | Height: | Size: 1.3 KiB |
Loading…
Reference in New Issue