puremagic 2.2.0__tar.gz → 2.2.1__tar.gz

puremagic-2.2.1/.github/workflows/master-source-guard.yml

@@ -0,0 +1,27 @@
+# Releases only: every change lands on develop first, then ships to master
+# as a single versioned release PR from develop.
+
+name: Master Source Guard
+
+on:
+  pull_request:
+    branches: [ master ]
+    types: [ opened, reopened, synchronize, edited ]
+
+permissions: {}
+
+jobs:
+  require-develop:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+    - name: Require PRs into master to come from develop
+      env:
+        HEAD_REF: ${{ github.head_ref }}
+        HEAD_REPO: ${{ github.event.pull_request.head.repo.full_name }}
+        BASE_REPO: ${{ github.repository }}
+      run: |
+        if [ "$HEAD_REF" != "develop" ] || [ "$HEAD_REPO" != "$BASE_REPO" ]; then
+          echo "::error::PRs into master must come from $BASE_REPO:develop (got $HEAD_REPO:$HEAD_REF). Please retarget this PR to develop."
+          exit 1
+        fi

puremagic-2.2.1/.github/workflows/pythonpublish.yml

@@ -0,0 +1,69 @@
+# Builds and publishes to PyPI when a GitHub release is created.
+# Uses PyPI Trusted Publishing (OIDC), so no PyPI password or token is stored in GitHub:
+# https://docs.pypi.org/trusted-publishers/
+# All actions are pinned to full commit SHAs; the comment shows the matching release tag.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+permissions: {}
+
+jobs:
+  build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    permissions:
+      contents: read
+
+    steps:
+    - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+      with:
+        persist-credentials: false
+
+    - name: Set up Python
+      uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0 # v7.1.0
+      with:
+        python-version: '3.15'
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@68559e99cc807c1eb7e9238fd43a15bba460eec2 # v10.3.3
+
+    - name: Install dependencies
+      run: uv sync --frozen
+
+    - name: Build and check distribution
+      run: |
+        uv build
+        uv run twine check dist/*
+
+    - name: Store distribution
+      uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+      with:
+        name: python-package-distributions
+        path: dist/
+        if-no-files-found: error
+
+  publish:
+    name: Publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    environment:
+      name: pypi
+      url: https://pypi.org/p/puremagic
+    permissions:
+      id-token: write  # Required for Trusted Publishing; the only permission this job has
+
+    steps:
+    - name: Download distribution
+      uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
+      with:
+        name: python-package-distributions
+        path: dist/
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@7245906fb61fa33a13554f9d5fb856fe61758086 # v1.14.3

{puremagic-2.2.0 → puremagic-2.2.1}/.github/workflows/tests.yml

@@ -16,24 +16,25 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.12", "3.13", "3.14"]
+        python-version: ["3.12", "3.13", "3.14", "3.15"]
         include:
           - os: macos-latest
-            python-version: '3.14'
+            python-version: '3.15'
           - os: windows-latest
-            python-version: '3.14'
+            python-version: '3.15'
     runs-on: ${{ matrix.os }}
+    timeout-minutes: 15
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@6d4fd22b20465ccc0f7354476588e8df7c9ca0e0 # v7.1.0
       with:
         python-version: ${{ matrix.python-version }}
         allow-prereleases: true
 
     - name: Install the latest version of uv and activate the environment
-      uses: astral-sh/setup-uv@v6
+      uses: astral-sh/setup-uv@68559e99cc807c1eb7e9238fd43a15bba460eec2 # v10.3.3
 
     - name: Install dependencies
       run: uv sync --frozen

{puremagic-2.2.0 → puremagic-2.2.1}/.pre-commit-config.yaml

@@ -35,7 +35,7 @@ repos:
 
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.15.5
+    rev: v0.17.3
     hooks:
       # Run the linter.
       - id: ruff-check
@@ -53,7 +53,7 @@ repos:
       pass_filenames: false
 
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.4.1
+    rev: v2.4.3
     hooks:
       - id: codespell
         args: [--ignore-words-list, "addin,caf,tye,wors"]
@@ -64,11 +64,11 @@ repos:
             )
 
 -   repo: https://github.com/tox-dev/pyproject-fmt
-    rev: v2.16.2
+    rev: v2.30.3
     hooks:
       - id: pyproject-fmt
 
 -   repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.25
+    rev: v0.27
     hooks:
       - id: validate-pyproject

{puremagic-2.2.0 → puremagic-2.2.1}/CHANGELOG.md

@@ -1,6 +1,19 @@
 Changelog
 =========
 
+Version 2.2.1
+-------------
+
+- Fixing #150 shell scripts with `#!/bin/sh`, `bash`, or `zsh` shebangs are now identified as `.sh` / `application/x-shellscript` instead of plain text (thanks to jbleyel and Sai Asish Y)
+- Fixing #152 CSV detection only sniffs a bounded sample, so large files (such as HTML exported from Excel as `.xls`) no longer take minutes to identify, and HTML starting with an uppercase `<HTML` tag is detected (thanks to nikilase)
+- Fixing #156 ISO media files (HEIC, AVIF, MP4, 3GP, MOV) are identified by their `ftyp` major brand instead of the box size (thanks to Nick Gigliotti and zhouh)
+- Fixing #157 CSV files with quoted delimiters, escaped quotes, or multiline fields are no longer rejected (thanks to zhouh)
+- Fixing #164 JPEG data without a filename hint now reports `.jpg` instead of `.jfif` (thanks to Gil Forcada Codinachs)
+- Fixing OpenDocument templates (`.ott`, `.ots`, `.otp`) are no longer reported as regular documents during ZIP scanning (thanks to pabszero)
+- Fixing file extensions are taken from the file's base name, so dots in directory names no longer produce bogus extensions (thanks to rui-zju)
+- Adding Python 3.15 to tested and supported versions
+- Changing PyPI releases to use Trusted Publishing, with GitHub Actions pinned to commit SHAs and upgraded off the deprecated Node.js 20 runtime
+
 Version 2.2.0
 -------------
 

{puremagic-2.2.0 → puremagic-2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: puremagic
-Version: 2.2.0
+Version: 2.2.1
 Summary: Pure python implementation of magic file detection
 Author-email: Chris Griffith <chris@cdgriffith.com>
 License-Expression: MIT
@@ -14,6 +14,7 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Classifier: Topic :: Utilities
 Requires-Python: >=3.12

{puremagic-2.2.0 → puremagic-2.2.1}/puremagic/__init__.py

@@ -1,3 +1,2 @@
-#!/usr/bin/env python
-from puremagic.main import *  # noqa: F403
+from puremagic.main import *
 from puremagic.main import __author__, __version__  # noqa: F401

{puremagic-2.2.0 → puremagic-2.2.1}/puremagic/magic_data.json

@@ -733,6 +733,7 @@
     ["437265617469766520566f6963652046696c651a", 0, ".voc", "audio/x-voc", "Creative Voice File"],
     ["595556344d504547",0, ".y4m", "video/x-yuv4mpeg", "YUV4MPEG2 video file"],
     ["3c68746d6c", 0, ".html", "text/html", "HTML File"],
+    ["3c48544d4c", 0, ".html", "text/html", "HTML File"],
     ["424c5545", 0, ".bvr", "", "Blue Iris Video File"],
     ["2d2d2d2d2d424547494e20504b4353372d2d2d2d2d", 0, ".p7b", "", "PKCS 7 Certificate File" ],
     ["7b22", 0, ".json", "application/json", "JSON File"],
@@ -856,6 +857,7 @@
     ],
     ["7a626578", 0, ".info", "", "ZoomBrowser Image Index"],
     ["425a68", 0, ".tbz2", "application/x-bzip2", "bzip2 compressed archive"],
+    ["ffd8ff", 0, ".jpg", "image/jpeg", "JPEG|EXIF|SPIFF images"],
     ["ffd8ff", 0, ".jfif", "image/jpeg", "JPEG|EXIF|SPIFF images"],
     ["514649", 0, ".qemu", "", "Qcow Disk Image"],
     ["504b5c3030335c303034", 0, ".epub", "application/epub+zip", "electronic book document"],
@@ -903,6 +905,19 @@
     ["23212f7573722f6c6f63616c2f62696e2f707974686f6e", 0, ".wsgi", "text/x-python", "Python script"],
     ["2321202f7573722f6c6f63616c2f62696e2f707974686f6e", 0, ".wsgi", "text/x-python", "Python script"],
     ["6576616c205c2265786563202f7573722f6c6f63616c2f62696e2f707974686f6e", 0, ".wsgi", "text/x-python", "Python script"],
+    ["23212f62696e2f7368", 0, ".sh", "application/x-sh", "POSIX shell script"],
+    ["2321202f62696e2f7368", 0, ".sh", "application/x-sh", "POSIX shell script"],
+    ["23212f7573722f62696e2f7368", 0, ".sh", "application/x-sh", "POSIX shell script"],
+    ["23212f7573722f62696e2f656e762073680a", 0, ".sh", "application/x-sh", "POSIX shell script"],
+    ["23212f62696e2f64617368", 0, ".sh", "application/x-sh", "Dash shell script"],
+    ["23212f62696e2f62617368", 0, ".sh", "application/x-shellscript", "Bash shell script"],
+    ["2321202f62696e2f62617368", 0, ".sh", "application/x-shellscript", "Bash shell script"],
+    ["23212f7573722f62696e2f62617368", 0, ".sh", "application/x-shellscript", "Bash shell script"],
+    ["23212f7573722f62696e2f656e762062617368", 0, ".sh", "application/x-shellscript", "Bash shell script"],
+    ["23212f7573722f6c6f63616c2f62696e2f62617368", 0, ".sh", "application/x-shellscript", "Bash shell script"],
+    ["23212f62696e2f7a7368", 0, ".sh", "application/x-shellscript", "Zsh shell script"],
+    ["23212f7573722f62696e2f7a7368", 0, ".sh", "application/x-shellscript", "Zsh shell script"],
+    ["23212f7573722f62696e2f656e76207a73680a", 0, ".sh", "application/x-shellscript", "Zsh shell script"],
     ["53756d6d6172793a20", 0, ".spec", "text/x-rpm-spec", "RPM spec file"],
     ["25646566696e6520", 0, ".spec", "text/x-rpm-spec", "RPM spec file"],
     ["667479707174", 4, ".qtvr", "video/quicktime", "QuickTime video"],
@@ -1144,7 +1159,6 @@
     ["b5a2b0b3b3b0a5b5", 0, ".cal", "", "Windows calendar"],
     ["537570657243616c", 0, ".cal", "", "SuperCalc worksheet"],
     ["504e4349554e444f", 0, ".dat", "", "Norton Disk Doctor undo file"],
-    ["0000001466747970", 0, ".3gp", "", "3GPP multimedia files"],
     ["5b57696e646f7773", 0, ".cpx", "", "Microsoft Code Page Translation file"],
     ["a90d000000000000", 0, ".dat", "", "Access Data FTK evidence"],
     ["424f4f4b4d4f4249", 0, ".prc", "", "Palmpilot resource file"],
@@ -1380,7 +1394,6 @@
     ["425a68", 0, ".bz2", "application/x-bzip2", "bzip2 compressed archive"],
     ["425a68", 0, ".tb2", "application/x-bzip2", "bzip2 compressed archive"],
     ["ffd8ff", 0, ".jpe", "image/jpeg", "JPEG|EXIF|SPIFF images"],
-    ["ffd8ff", 0, ".jpg", "image/jpeg", "JPEG|EXIF|SPIFF images"],
     ["2d6c68", 2, ".lha", "application/x-lha", "Compressed archive"],
     ["445644", 0, ".dvr", "", "DVR-Studio stream file"],
     ["1a0000", 0, ".ntf", "", "Lotus Notes database template"],
@@ -1655,6 +1668,7 @@
     ["fff0", 0, ".aac", "audio/aac", "AAC audio"],
     ["667479704d3441", 4, ".f4a", "audio/mp4", "MPEG-4 audio"],
     ["6674797069736f6d", 4, ".mp4", "video/mp4", "MPEG-4 video"],
+    ["667479706d703431", 4, ".mp4", "video/mp4", "MPEG-4 video"],
     ["667479706d703432", 4, ".mp4", "video/mp4", "MPEG-4 video"],
     ["667479704d534e56", 4, ".mp4", "video/mp4", "MPEG-4 video"],
     ["667479704d345620", 4, ".mp4", "video/mp4", "MPEG-4 video"],
@@ -2040,7 +2054,6 @@
     ["fff9", 0, ".aac", "audio/aac", "MPEG-2 AAC audio"],
     ["fff1", 0, ".aac", "audio/aac", "MPEG-4 AAC audio"],
     ["6674797033677035", 4, ".mp4", "video/mp4", "MPEG-4 video file"],
-    ["0000001c66747970", 0, ".mp4", "video/mp4", "MPEG-4 video"],
     ["fdffffff02", 512, ".pub", "", "MS Publisher file subheader"],
     ["53505642", 0, ".spvb", "", "MultiBit Bitcoin blockchain file"],
     ["0a166f72672e626974636f696e2e7072", 0, ".wallet", "", "MultiBit Bitcoin wallet file"],

{puremagic-2.2.0 → puremagic-2.2.1}/puremagic/main.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 """
 puremagic is a pure python module that will identify a file based off it's
 magic numbers. It is designed to be minimalistic and inherently cross-platform
@@ -23,38 +22,39 @@ import puremagic
 
 if os.getenv("PUREMAGIC_DEEPSCAN") != "0":
     from puremagic.scanners import (
-        zip_scanner,
-        pdf_scanner,
-        text_scanner,
+        asf_scanner,
+        cfbf_scanner,
+        ebml_scanner,
+        hdf5_scanner,
         json_scanner,
-        python_scanner,
-        sndhdr_scanner,
         mpeg_audio_scanner,
-        hdf5_scanner,
-        cfbf_scanner,
         ogg_scanner,
-        asf_scanner,
-        ebml_scanner,
+        pdf_scanner,
+        python_scanner,
+        sndhdr_scanner,
+        text_scanner,
+        zip_scanner,
     )
 
 __author__ = "Chris Griffith"
-__version__ = "2.2.0"
+__version__ = "2.2.1"
 __all__ = [
-    "magic_file",
-    "magic_string",
-    "magic_stream",
-    "magic_extension",
-    "from_file",
-    "from_string",
-    "from_stream",
-    "from_extension",
-    "ext_from_filename",
     "PureError",
     "PureMagic",
     "PureMagicWithConfidence",
+    "ext_from_filename",
+    "from_extension",
+    "from_file",
+    "from_stream",
+    "from_string",
+    "magic_extension",
+    "magic_file",
+    "magic_stream",
+    "magic_string",
 ]
 
 here = os.path.abspath(os.path.dirname(__file__))
+DEFAULT_MAGIC_DATA = os.path.join(here, "magic_data.json")
 
 PureMagic = namedtuple(
     "PureMagic",
@@ -88,7 +88,7 @@ class PureValueError(ValueError):
 
 
 def magic_data(
-    filename: os.PathLike | str = os.path.join(here, "magic_data.json"),
+    filename: os.PathLike | str = DEFAULT_MAGIC_DATA,
 ) -> tuple[list[PureMagic], list[PureMagic], list[PureMagic], dict[bytes, list[PureMagic]]]:
     """Read the magic file"""
     with open(filename, encoding="utf-8") as f:
@@ -270,7 +270,7 @@ def ext_from_filename(filename: os.PathLike | str) -> str:
     :return: the extension off the end (empty string if it can't find one)
     """
     try:
-        base, ext = str(filename).lower().rsplit(".", 1)
+        base, ext = os.path.basename(filename).lower().rsplit(".", 1)
     except ValueError:
         return ""
     ext = f".{ext}"
@@ -529,22 +529,18 @@ def run_deep_scan(
                         name=result.name,
                     )
                 ]
-        try:
-            result = catch_all_deep_scan(filename, head, foot)
-        except Exception:
-            raise
-        else:
-            if result:
-                return [
-                    PureMagicWithConfidence(
-                        confidence=result.confidence,
-                        byte_match=None,
-                        offset=None,
-                        extension=result.extension,
-                        mime_type=result.mime_type,
-                        name=result.name,
-                    )
-                ]
+        result = catch_all_deep_scan(filename, head, foot)
+        if result:
+            return [
+                PureMagicWithConfidence(
+                    confidence=result.confidence,
+                    byte_match=None,
+                    offset=None,
+                    extension=result.extension,
+                    mime_type=result.mime_type,
+                    name=result.name,
+                )
+            ]
         if raise_on_none:
             raise PureError("Could not identify file")
 
@@ -594,8 +590,8 @@ def run_deep_scan(
 
 
 def command_line_entry(*args):
-    import sys  # noqa: PLC0415
-    from argparse import ArgumentParser  # noqa: PLC0415
+    import sys
+    from argparse import ArgumentParser
 
     parser = ArgumentParser(
         description=(

{puremagic-2.2.0 → puremagic-2.2.1}/puremagic/scanners/cfbf_scanner.py

@@ -115,9 +115,8 @@ def main(file_path: os.PathLike, head: bytes, foot: bytes) -> Match | None:
         return None
 
     # Verify magic bytes
-    if head[:8] != match_bytes:
-        if head[:4] != match_bytes_short:
-            return None
+    if head[:8] != match_bytes and head[:4] != match_bytes_short:
+        return None
 
     # Parse CFBF header
     sector_shift = struct.unpack_from("<H", head, 30)[0]