Merge branch 'master' into patch-1

Author: CatKasha

.coveragerc

@@ -0,0 +1,14 @@
+[run]
+branch = True
+
+omit =
+    examples/*
+    tests/*
+
+source = filetype
+
+[report]
+exclude_lines =
+    # Don't complain if non-runnable code isn't run:
+    if __name__ == ['"]+__main__['"]+:
+    if ['"]+__main__['"]+ == __name__:

.github/workflows/test.yml

@@ -0,0 +1,59 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+
+# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
+
+  release_test:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ ubuntu-latest ]
+        python-version: ["3.9"]
+
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        fetch-depth: 0
+        ref: ${{ github.event.pull_request.head.sha }}
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Upgrade PIP
+      run: python -m pip install --upgrade pip
+
+    - name: Install application with ML
+      run: python -m pip install .
+
+    - name: CLI tool check
+      run: filetype --help
+
+    - name: Install test framework dependencies
+      run: python -m pip install tox
+
+    - name: Run tox pipeline
+      run: tox
+
+    - name: HTML coverage reports
+      if: always()
+      uses: actions/upload-artifact@v2
+      with:
+        name: coverage_${{ matrix.python-version }}
+        path: coverage
+

History.md

@@ -1,4 +1,68 @@
 
+v1.2.0 / 2022-11-02
+===================
+
+  * chore(version): bump minor
+  * Merge pull request #147 from sayanarijit/fix-146
+  * Add tests for m4a
+  * Try matching audio before video
+  * Merge pull request #145 from RSabet/master
+  * update README to include avif
+  * added image filetype avif
+  * Update __init__.py
+  * Merge pull request #141 from ferstar/master
+  * test: remove unused imported(F401)
+  * refactor: duck-typing reading magic string and try to restore the reader position if possible
+  * test: fix E275 missing whitespace after keyword
+  * test: Use tox pipeline instead of pytest
+  * test: ignore E501 error for flake8 check
+  * fix: CLI params parser
+  * Merge pull request #137 from ferstar/master
+  * fix: guess ".docx" func and add another doc file test case
+  * fix: guess ".doc" func and add another doc file test case
+  * test: skip benchmark test in tox config
+  * fix: restore reader position after retrieving signature bytes
+  * Merge pull request #136 from ferstar/master
+  * test: no need to skip zstd test case
+  * Merge pull request #135 from ferstar/master
+  * fix: regression for file-like obj file type detection
+  * Merge pull request #134 from babenek/actions
+  * Merge pull request #129 from ferstar/master
+  * Merge branch 'master' into master
+  * Merge pull request #133 from magbyr/master
+  * Merge pull request #131 from babenek/master
+  * CI workflow in github actions
+  * Changed to if statements in matching method
+  * Changed return method because of coverage calculation problems
+  * Extra line at EOF
+  * Extra line at EOF
+  * Extra line at EOF
+  * Apply suggestions from code review
+  * README changes
+  * Linter changes
+  * Added document filetypes for doc, docx, odt, xls, xlsx, ods, ppt, pptx and odp. Added tests and sample documents for document filetypes
+  * Fix undocumented exception
+  * style: Simplify binary to integer method
+  * feat: add zstd skippable frames support
+  * test: fix the tox config and missing test sample files
+  * test: fix the zst test sample file
+  * fix(readme): rst syntax wtf
+
+v1.1.0 / 2022-07-12
+===================
+
+  * feat(version): bump minor
+  * Merge pull request #127 from ferstar/master
+  * Merge pull request #123 from levrik/patch-1
+  * Merge pull request #126 from babenek/master
+  * docs: add zstd type
+  * fix: remove unnecessary duck-typing try
+  * feat: add zst(d) type
+  * chore: fix lint errors
+  * test: fix memoryview test cases
+  * BugFix for uncaught exceptions
+  * Support PDF with BOM
+
 v1.0.13 / 2022-04-21
 ====================
 

README.rst

@@ -77,6 +77,7 @@ Image
 -  **psd** - ``image/vnd.adobe.photoshop``
 -  **ico** - ``image/x-icon``
 -  **heic** - ``image/heic``
+-  **avif** - ``image/avif``
 
 Video
 ^^^^^
@@ -122,7 +123,6 @@ Archive
 -  **pdf** - ``application/pdf``
 -  **exe** - ``application/x-msdownload``
 -  **swf** - ``application/x-shockwave-flash``
-
 -  **rtf** - ``application/rtf``
 -  **eot** - ``application/octet-stream``
 -  **ps** - ``application/postscript``
@@ -136,6 +136,20 @@ Archive
 -  **lzo** - ``application/x-lzop``
 -  **lz** - ``application/x-lzip``
 -  **lz4** - ``application/x-lz4``
+-  **zstd** - ``application/zstd``
+
+Document
+^^^^^^^^
+
+-  **doc** - ``application/msword``
+-  **docx** - ``application/vnd.openxmlformats-officedocument.wordprocessingml.document``
+-  **odt** - ``application/vnd.oasis.opendocument.text``
+-  **xls** - ``application/vnd.ms-excel``
+-  **xlsx** - ``application/vnd.openxmlformats-officedocument.spreadsheetml.sheet``
+-  **ods** - ``application/vnd.oasis.opendocument.spreadsheet``
+-  **ppt** - ``application/vnd.ms-powerpoint``
+-  **pptx** - ``application/vnd.openxmlformats-officedocument.presentationml.presentation``
+-  **odp** - ``application/vnd.oasis.opendocument.presentation``
 
 Font
 ^^^^

filetype/__init__.py

@@ -7,4 +7,4 @@
 from .match import *  # noqa
 
 # Current package semver version
-__version__ = version = '1.0.13'
+__version__ = version = '1.2.0'

filetype/__main__.py

@@ -1,3 +1,5 @@
+import sys
+
 import filetype
 
 
@@ -12,17 +14,23 @@ def guess(path):
 def main():
     import argparse
 
-    parser = argparse.ArgumentParser(description='Determine type of FILEs.')
-    parser.add_argument("file", nargs='+')
-    parser.add_argument('-v', '--version', action='store_true',
-                        help='output version information and exit')
+    parser = argparse.ArgumentParser(
+        prog='filetype', description='Determine type of FILEs.'
+    )
+    parser.add_argument('-f', '--file', nargs='+')
+    parser.add_argument(
+        '-v', '--version', action='version',
+        version='%(prog)s ' + filetype.version,
+        help='output version information and exit'
+    )
+
     args = parser.parse_args()
+    if len(sys.argv) < 2:
+        parser.print_help()
+        sys.exit(1)
 
-    if args.version:
-        print(filetype.version)
-    else:
-        for i in args.file:
-            guess(i)
+    for i in args.file:
+        guess(i)
 
 
 if __name__ == '__main__':

filetype/filetype.py

@@ -14,7 +14,7 @@ def guess(obj):
     Infers the type of the given input.
 
     Function is overloaded to accept multiple types in input
-    and peform the needed type inference based on it.
+    and perform the needed type inference based on it.
 
     Args:
         obj: path to file, bytes or bytearray.

filetype/helpers.py

@@ -3,7 +3,7 @@
 from __future__ import absolute_import
 from .types import TYPES
 from .match import (
-    image_match, font_match,
+    image_match, font_match, document_match,
     video_match, audio_match, archive_match
 )
 
@@ -122,3 +122,19 @@ def is_font(obj):
         TypeError: if obj is not a supported type.
     """
     return font_match(obj) is not None
+
+
+def is_document(obj):
+    """
+    Checks if a given input is a supported type document.
+
+    Args:
+        obj: path to file, bytes or bytearray.
+
+    Returns:
+        True if obj is a valid document. Otherwise False.
+
+    Raises:
+        TypeError: if obj is not a supported type.
+    """
+    return document_match(obj) is not None

filetype/match.py

@@ -5,6 +5,7 @@
 from .types import ARCHIVE as archive_matchers
 from .types import AUDIO as audio_matchers
 from .types import APPLICATION as application_matchers
+from .types import DOCUMENT as document_matchers
 from .types import FONT as font_matchers
 from .types import IMAGE as image_matchers
 from .types import VIDEO as video_matchers
@@ -135,3 +136,20 @@ def application_match(obj):
         TypeError: if obj is not a supported type.
     """
     return match(obj, application_matchers)
+
+
+def document_match(obj):
+    """
+    Matches the given input against the available
+    document type matchers.
+
+    Args:
+        obj: path to file, bytes or bytearray.
+
+    Returns:
+        Type instance if matches. Otherwise None.
+
+    Raises:
+        TypeError: if obj is not a supported type.
+    """
+    return match(obj, document_matchers)

filetype/types/__init__.py

@@ -5,6 +5,7 @@
 from . import archive
 from . import audio
 from . import application
+from . import document
 from . import font
 from . import image
 from . import video
@@ -28,6 +29,7 @@
     image.Ico(),
     image.Heic(),
     image.Dcm(),
+    image.Avif(),
 )
 
 # Supported video types
@@ -90,13 +92,27 @@
     archive.Lz(),
     archive.Elf(),
     archive.Lz4(),
+    archive.Zstd(),
 )
 
 # Supported archive container types
 APPLICATION = (
     application.Wasm(),
 )
 
+# Supported document types
+DOCUMENT = (
+    document.Doc(),
+    document.Docx(),
+    document.Odt(),
+    document.Xls(),
+    document.Xlsx(),
+    document.Ods(),
+    document.Ppt(),
+    document.Pptx(),
+    document.Odp(),
+)
+
 
 # Expose supported type matchers
-TYPES = list(VIDEO + IMAGE + AUDIO + FONT + ARCHIVE + APPLICATION)
+TYPES = list(IMAGE + AUDIO + VIDEO + FONT + DOCUMENT + ARCHIVE + APPLICATION)