Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
mat2
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Monitor
Service Desk
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
jvoisin
mat2
Commits
8c26020f
Commit
8c26020f
authored
1 year ago
by
Jason Smalls
Committed by
jvoisin
1 year ago
Browse files
Options
Downloads
Patches
Plain Diff
Add more files to ignore for MSOffice documents
parent
a0c97b25
Branches
Branches containing commit
Tags
Tags containing commit
No related merge requests found
Pipeline
#154598
passed with warnings
1 year ago
Stage: linting
Stage: test
Changes
1
Pipelines
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
libmat2/office.py
+28
-4
28 additions, 4 deletions
libmat2/office.py
with
28 additions
and
4 deletions
libmat2/office.py
+
28
−
4
View file @
8c26020f
...
@@ -63,8 +63,20 @@ class MSOfficeParser(ZipParser):
...
@@ -63,8 +63,20 @@ class MSOfficeParser(ZipParser):
'
application/vnd.openxmlformats-officedocument.wordprocessingml.footer+xml
'
,
# /word/footer.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.footer+xml
'
,
# /word/footer.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.header+xml
'
,
# /word/header.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.header+xml
'
,
# /word/header.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml
'
,
# /word/styles.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml
'
,
# /word/styles.xml
'
application/vnd.openxmlformats-officedocument.wordprocessingml.numbering+xml
'
,
# /word/numbering.xml (used for bullet point formatting)
'
application/vnd.openxmlformats-officedocument.theme+xml
'
,
# /word/theme/theme[0-9].xml (used for font and background coloring, etc.)
'
application/vnd.openxmlformats-package.core-properties+xml
'
,
# /docProps/core.xml
'
application/vnd.openxmlformats-package.core-properties+xml
'
,
# /docProps/core.xml
# for more complicated powerpoints
'
application/vnd.openxmlformats-officedocument.presentationml.notesSlide+xml
'
,
'
application/vnd.openxmlformats-officedocument.presentationml.notesMaster+xml
'
,
'
application/vnd.openxmlformats-officedocument.presentationml.handoutMaster+xml
'
,
'
application/vnd.openxmlformats-officedocument.drawingml.diagramData+xml
'
,
'
application/vnd.openxmlformats-officedocument.drawingml.diagramLayout+xml
'
,
'
application/vnd.openxmlformats-officedocument.drawingml.diagramStyle+xml
'
,
'
application/vnd.openxmlformats-officedocument.drawingml.diagramColors+xml
'
,
'
application/vnd.ms-office.drawingml.diagramDrawing+xml
'
,
# Do we want to keep the following ones?
# Do we want to keep the following ones?
'
application/vnd.openxmlformats-officedocument.wordprocessingml.settings+xml
'
,
'
application/vnd.openxmlformats-officedocument.wordprocessingml.settings+xml
'
,
}
}
...
@@ -85,7 +97,7 @@ class MSOfficeParser(ZipParser):
...
@@ -85,7 +97,7 @@ class MSOfficeParser(ZipParser):
r
'
^_rels/\.rels$
'
,
r
'
^_rels/\.rels$
'
,
r
'
^xl/sharedStrings\.xml$
'
,
# https://docs.microsoft.com/en-us/office/open-xml/working-with-the-shared-string-table
r
'
^xl/sharedStrings\.xml$
'
,
# https://docs.microsoft.com/en-us/office/open-xml/working-with-the-shared-string-table
r
'
^xl/calcChain\.xml$
'
,
r
'
^xl/calcChain\.xml$
'
,
r
'
^(?:word|ppt|xl)/_rels/document\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/_rels/
(
document
|workbook|presentation)
\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/_rels/footer[0-9]*\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/_rels/footer[0-9]*\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/_rels/header[0-9]*\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/_rels/header[0-9]*\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/charts/_rels/chart[0-9]+\.xml\.rels$
'
,
r
'
^(?:word|ppt|xl)/charts/_rels/chart[0-9]+\.xml\.rels$
'
,
...
@@ -100,6 +112,7 @@ class MSOfficeParser(ZipParser):
...
@@ -100,6 +112,7 @@ class MSOfficeParser(ZipParser):
r
'
^ppt/slideLayouts/_rels/slideLayout[0-9]+\.xml\.rels$
'
,
r
'
^ppt/slideLayouts/_rels/slideLayout[0-9]+\.xml\.rels$
'
,
r
'
^ppt/slideLayouts/slideLayout[0-9]+\.xml$
'
,
r
'
^ppt/slideLayouts/slideLayout[0-9]+\.xml$
'
,
r
'
^(?:word|ppt|xl)/tableStyles\.xml$
'
,
r
'
^(?:word|ppt|xl)/tableStyles\.xml$
'
,
r
'
^(?:word|ppt|xl)/tables/table[0-9]+\.xml$
'
,
r
'
^ppt/slides/_rels/slide[0-9]*\.xml\.rels$
'
,
r
'
^ppt/slides/_rels/slide[0-9]*\.xml\.rels$
'
,
r
'
^ppt/slides/slide[0-9]*\.xml$
'
,
r
'
^ppt/slides/slide[0-9]*\.xml$
'
,
# https://msdn.microsoft.com/en-us/library/dd908153(v=office.12).aspx
# https://msdn.microsoft.com/en-us/library/dd908153(v=office.12).aspx
...
@@ -109,8 +122,13 @@ class MSOfficeParser(ZipParser):
...
@@ -109,8 +122,13 @@ class MSOfficeParser(ZipParser):
r
'
^ppt/slideMasters/slideMaster[0-9]+\.xml
'
,
r
'
^ppt/slideMasters/slideMaster[0-9]+\.xml
'
,
r
'
^ppt/slideMasters/_rels/slideMaster[0-9]+\.xml\.rels
'
,
r
'
^ppt/slideMasters/_rels/slideMaster[0-9]+\.xml\.rels
'
,
r
'
^xl/worksheets/_rels/sheet[0-9]+\.xml\.rels
'
,
r
'
^xl/worksheets/_rels/sheet[0-9]+\.xml\.rels
'
,
r
'
^xl/drawings/vmlDrawing[0-9]+\.vml
'
,
r
'
^(?:word|ppt|xl)/drawings/vmlDrawing[0-9]+\.vml
'
,
r
'
^xl/drawings/drawing[0-9]+\.xml
'
,
r
'
^(?:word|ppt|xl)/drawings/drawing[0-9]+\.xml
'
,
r
'
^(?:word|ppt|xl)/embeddings/Microsoft_Excel_Worksheet[0-9]+\.xlsx
'
,
# rels for complicated powerpoints
r
'
^ppt/notesSlides/_rels/notesSlide[0-9]+\.xml\.rels
'
,
r
'
^ppt/notesMasters/_rels/notesMaster[0-9]+\.xml\.rels
'
,
r
'
^ppt/handoutMasters/_rels/handoutMaster[0-9]+\.xml\.rels
'
,
}))
}))
self
.
files_to_omit
=
set
(
map
(
re
.
compile
,
{
# type: ignore
self
.
files_to_omit
=
set
(
map
(
re
.
compile
,
{
# type: ignore
r
'
^\[trash\]/
'
,
r
'
^\[trash\]/
'
,
...
@@ -120,18 +138,24 @@ class MSOfficeParser(ZipParser):
...
@@ -120,18 +138,24 @@ class MSOfficeParser(ZipParser):
r
'
^(?:word|ppt|xl)/printerSettings/
'
,
r
'
^(?:word|ppt|xl)/printerSettings/
'
,
r
'
^(?:word|ppt|xl)/theme
'
,
r
'
^(?:word|ppt|xl)/theme
'
,
r
'
^(?:word|ppt|xl)/people\.xml$
'
,
r
'
^(?:word|ppt|xl)/people\.xml$
'
,
r
'
^(?:word|ppt|xl)/persons/person\.xml$
'
,
r
'
^(?:word|ppt|xl)/numbering\.xml$
'
,
r
'
^(?:word|ppt|xl)/numbering\.xml$
'
,
r
'
^(?:word|ppt|xl)/tags/
'
,
r
'
^(?:word|ppt|xl)/tags/
'
,
r
'
^(?:word|ppt|xl)/glossary/
'
,
# View properties like view mode, last viewed slide etc
# View properties like view mode, last viewed slide etc
r
'
^(?:word|ppt|xl)/viewProps\.xml$
'
,
r
'
^(?:word|ppt|xl)/viewProps\.xml$
'
,
# Additional presentation-wide properties like printing properties,
# Additional presentation-wide properties like printing properties,
# presentation show properties etc.
# presentation show properties etc.
r
'
^(?:word|ppt|xl)/presProps\.xml$
'
,
r
'
^(?:word|ppt|xl)/presProps\.xml$
'
,
r
'
^(?:word|ppt|xl)/comments[0-9]+\.xml$
'
,
r
'
^(?:word|ppt|xl)/comments[0-9]+\.xml$
'
,
r
'
^(?:word|ppt|xl)/threadedComments/threadedComment[0-9]*\.xml$
'
,
r
'
^(?:word|ppt|xl)/commentsExtended\.xml$
'
,
r
'
^(?:word|ppt|xl)/commentsExtensible\.xml$
'
,
r
'
^(?:word|ppt|xl)/commentsIds\.xml$
'
,
# we have an allowlist in self.files_to_keep,
# we have an allowlist in self.files_to_keep,
# so we can trash everything else
# so we can trash everything else
r
'
^(?:word|ppt|xl)/_rels/
'
,
r
'
^(?:word|ppt|xl)/_rels/
'
,
r
'
docMetadata/LabelInfo\.xml$
'
}))
}))
if
self
.
__fill_files_to_keep_via_content_types
()
is
False
:
if
self
.
__fill_files_to_keep_via_content_types
()
is
False
:
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment