Finalize version 3.1.0 (#212)

Author: ianare

.github/workflows/linting.yml

@@ -17,7 +17,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v4
       with:
-        python-version: "3.10"
+        python-version: "3.11"
 
     - name: Cache dependencies
       uses: actions/cache@v3
@@ -30,7 +30,7 @@ jobs:
     - name: Install dependencies
       run: |
         pip install virtualenv
-        make venv reqs-install
+        make venv install-dev
 
     - name: Static analysis of the code
       run: |

.github/workflows/test.yml

@@ -40,13 +40,16 @@ jobs:
 
     - name: Install
       run: |
-        pip install -e .
+        pip install virtualenv
+        make venv install
 
     - name: Run in debug and color mode
       run: |
+        source .venv/bin/activate
         make test
 
     - name: Compare image processing output
       run: |
+        source .venv/bin/activate
         make test-diff
 

.pylintrc

@@ -59,10 +59,11 @@ ignore-paths=
 # Emacs file locks
 ignore-patterns=^\.#
 
-# List of module names for which member attributes should not be checked
-# (useful for modules/projects where namespaces are manipulated during runtime
-# and thus existing member attributes cannot be deduced by static analysis). It
-# supports qualified module names, as well as Unix pattern matching.
+# List of module names for which member attributes should not be checked and
+# will not be imported (useful for modules/projects where namespaces are
+# manipulated during runtime and thus existing member attributes cannot be
+# deduced by static analysis). It supports qualified module names, as well as
+# Unix pattern matching.
 ignored-modules=
 
 # Python code to execute, usually for sys.path manipulation such as
@@ -86,6 +87,10 @@ load-plugins=
 # Pickle collected data for later comparisons.
 persistent=yes
 
+# Resolve imports to .pyi stubs if available. May reduce no-member messages and
+# increase not-an-iterable messages.
+prefer-stubs=no
+
 # Minimum Python version to use for version dependent checks. Will default to
 # the version used to run pylint.
 py-version=3.7
@@ -190,10 +195,7 @@ good-names=i,
            k,
            ex,
            Run,
-           _,
-           s,
-           fh,
-           EXIF
+           _
 
 # Good variable names regexes, separated by a comma. If names match any regex,
 # they will always be accepted
@@ -305,6 +307,9 @@ max-locals=25
 # Maximum number of parents for a class (see R0901).
 max-parents=7
 
+# Maximum number of positional arguments for function / method.
+max-positional-arguments=10
+
 # Maximum number of public methods for a class (see R0904).
 max-public-methods=20
 
@@ -429,13 +434,12 @@ disable=raw-checker-failed,
         locally-disabled,
         file-ignored,
         suppressed-message,
-        useless-suppression,
         deprecated-pragma,
         use-symbolic-message-instead,
         use-implicit-booleaness-not-comparison-to-string,
         use-implicit-booleaness-not-comparison-to-zero,
-        consider-using-f-string,
         missing-function-docstring,
+        consider-using-f-string,
         fixme,
 
 # Enable the message, report, category or checker with the given id(s). You can
@@ -474,6 +478,11 @@ max-nested-blocks=5
 # printed.
 never-returning-functions=sys.exit,argparse.parse_error
 
+# Let 'consider-using-join' be raised when the separator to join on would be
+# non-empty (resulting in expected fixes of the type: ``"- " + " -
+# ".join(items)``)
+suggest-join-with-non-empty-separator=yes
+
 
 [REPORTS]
 
@@ -488,10 +497,10 @@ evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor
 # used to format the message information. See doc for all details.
 msg-template=
 
-# Set the output format. Available formats are: text, parseable, colorized,
-# json2 (improved json format), json (old json format) and msvs (visual
-# studio). You can also give a reporter class, e.g.
-# mypackage.mymodule.MyReporterClass.
+# Set the output format. Available formats are: 'text', 'parseable',
+# 'colorized', 'json2' (improved json format), 'json' (old json format), msvs
+# (visual studio) and 'github' (GitHub actions). You can also give a reporter
+# class, e.g. mypackage.mymodule.MyReporterClass.
 #output-format=
 
 # Tells whether to display a full report or only the messages.

ChangeLog.rst

@@ -1,7 +1,14 @@
 EXIF.py Change Log
 ##################
 
-3.1.0 — 2023-05-??
+3.1.0 — 2025-04-25
+    * Add more typing definitions (#181)
+    * Put all test files in the repo (#208)
+    * use pre-commit to run black, isort, pylint, mypy (#209)
+    * Canon MakerNote: Allow callable to process tag value (#189) by Daan van Gorkum
+    * Added missing HEIC box names and handling of a TIFF header inside HEIC (#173) by Antti Ketola
+    * don't let debug logging trigger an exception (#196) by David Bonner
+    * fix for certain box names not handled, but skipping would generate valid output by Anand Mahesh
     * Add DJI makernotes, extract_thumbnail parameter (#168) by Piero Toffanin
     * Fix endianess bug while reading DJI makernotes, add Make tag (#169) by Piero Toffanin
     * Make CI pass (#178) by Nick Dimitroff

LICENSE.txt

@@ -37,8 +37,11 @@ test-diff: ## Run and compare exif dump
 analyze: ## Run all static analysis tools
 	$(PRE_COMMIT_BIN) run --all
 
-reqs-install: ## Install with all requirements
-	$(PIP_INSTALL) .[dev]
+install-dev: ## Install with all development requirements
+	$(PIP_INSTALL) -U -e .[dev]
+
+install: ## Install with basic requirements
+	$(PIP_INSTALL) -U -e .
 
 build:  ## build distribution
 	rm -fr ./dist

Makefile

@@ -4,6 +4,8 @@ EXIF.py
 
 Easy to use Python module to extract Exif metadata from digital image files.
 
+Pure Python, lightweight, no dependencies.
+
 Supported formats: TIFF, JPEG, PNG, Webp, HEIC
 
 
@@ -12,10 +14,6 @@ Compatibility
 
 EXIF.py is tested and officially supported on Python 3.7 to 3.13
 
-Starting with version ``3.0.0``, Python2 compatibility is dropped *completely* (syntax errors due to type hinting).
-
-https://pythonclock.org/
-
 
 Installation
 ************
@@ -36,9 +34,9 @@ Development Version
 
 After cloning the repo, use the provided Makefile::
 
-  make venv reqs-install
+  make venv install-dev
 
-Which will install a virtual environment and install development dependencies.
+Which will create a virtual environment and install development dependencies.
 
 Usage
 *****
@@ -163,7 +161,8 @@ Pass the ``-s`` or ``--strict`` argument, or as:
 Built-in Types
 ==============
 
-For easier serialization and programmatic use, this option returns a dictionary with values in built-in Python types (int, float, str, bytes, list, None) instead of `IfdTag` objects.
+For easier serialization and programmatic use, this option returns a dictionary with values in built-in Python types
+(int, float, str, bytes, list, None) instead of `IfdTag` objects.
 
 Pass the ``-b`` or ``--builtin`` argument, or as:
 
@@ -226,7 +225,7 @@ License
 
 Copyright © 2002-2007 Gene Cash
 
-Copyright © 2007-2023 Ianaré Sévi and contributors
+Copyright © 2007-2025 Ianaré Sévi and contributors
 
 A **huge** thanks to all the contributors over the years!
 

README.rst

@@ -4,7 +4,7 @@
 """
 
 import struct
-from typing import BinaryIO, Dict, Tuple
+from typing import Any, BinaryIO, Dict, Tuple
 
 from exifread.classes import ExifHeader
 from exifread.exceptions import ExifNotFound, InvalidExif
@@ -37,8 +37,13 @@ def _find_tiff_exif(fh: BinaryIO) -> Tuple[int, bytes]:
     return offset, endian
 
 
-def _find_heic_tiff(fh: BinaryIO) -> tuple:
-    """In some HEIC files, the Exif offset is 0 and there is a plain TIFF header near end of the file."""
+def _find_heic_tiff(fh: BinaryIO) -> Tuple[int, bytes]:
+    """
+    Look for TIFF header in HEIC files.
+
+    In some HEIC files, the Exif offset is 0,
+    and yet there is a plain TIFF header near end of the file.
+    """
 
     data = fh.read(4)
     if data[0:2] in [b"II", b"MM"] and data[2] == 42 and data[3] == 0:
@@ -126,7 +131,7 @@ def _get_xmp(fh: BinaryIO) -> bytes:
     return xmp_bytes
 
 
-def _determine_type(fh: BinaryIO) -> tuple:
+def _determine_type(fh: BinaryIO) -> Tuple[int, bytes, int]:
     # by default do not fake an EXIF beginning
     fake_exif = 0
 
@@ -163,7 +168,7 @@ def process_file(
     auto_seek=True,
     extract_thumbnail=True,
     builtin_types=False,
-) -> dict:
+) -> Dict[str, Any]:
     """
     Process an image file (expects an open file object).
 
@@ -175,22 +180,22 @@ def process_file(
         fh.seek(0)
 
     try:
-        offset, endian, fake_exif = _determine_type(fh)
+        offset, endian_bytes, fake_exif = _determine_type(fh)
     except ExifNotFound as err:
         logger.warning(err)
         return {}
     except InvalidExif as err:
         logger.debug(err)
         return {}
 
-    endian = chr(ord_(endian[0]))
+    endian_str = chr(ord_(endian_bytes[0]))
     # deal with the EXIF info we found
     logger.debug(
-        "Endian format is %s (%s)", endian, ENDIAN_TYPES.get(endian, "Unknown")
+        "Endian format is %s (%s)", endian_str, ENDIAN_TYPES.get(endian_str, "Unknown")
     )
 
     hdr = ExifHeader(
-        fh, endian, offset, fake_exif, strict, debug, details, truncate_tags
+        fh, endian_str, offset, fake_exif, strict, debug, details, truncate_tags
     )
     ifd_list = hdr.list_ifd()
     thumb_ifd = 0

exifread/__init__.py

@@ -0,0 +1,6 @@
+"""Main entrypoint for the module."""
+
+from exifread.cli import main
+
+if __name__ == "__main__":
+    main()

exifread/__main__.py

@@ -83,7 +83,7 @@ def __init__(
         file_handle: BinaryIO,
         endian: str,
         offset: int,
-        fake_exif,
+        fake_exif: int,
         strict: bool,
         debug=False,
         detailed=True,
@@ -431,7 +431,9 @@ def extract_tiff_thumbnail(self, thumb_ifd: int) -> None:
             old_offset = self.s2n(entry + 8, 4)
             # start of the 4-byte pointer area in entry
             ptr = i * 12 + 18
-            # remember strip offsets location
+
+            # remember strip offsets
+            strip_len = 0
             if tag == 0x0111:
                 strip_off = ptr
                 strip_len = count * type_length