[script.module.iptcinfo3] 2.2.0

Author: ronie

script.module.iptcinfo3/CHANGELOG.md

@@ -1,3 +1,27 @@
+## 2.2.0 (2025-10-02)
+
+### Bug Fixes
+- **Issue #40**: Clarified license statements - now consistently states "Artistic-1.0 OR GPL-1.0-or-later"
+- **Issue #24**: Changed "Marker scan hit start of image data" to INFO level when `force=True` is used
+- **Issue #32**: Fixed charset recognition for ISO 2022 escape sequences (UTF-8 as `\x1b%G`)
+- **Issue #26**: Added validation for float/NaN values in `packedIIMData()` to prevent TypeError
+
+### New Features
+- **Issue #35**: Added 'credit line' field support per IPTC Core 1.1 (backward compatible with 'credit')
+- **Issue #42**: Added 'destination' field as alias for 'original transmission reference'
+
+### Improvements
+- **Issue #15**: Enhanced IPTC tag collection with better field mappings
+- **Issue #38**: Verified backup file behavior (use `options={'overwrite': True}` to avoid ~ files)
+- Better error handling and logging throughout
+
+### Notes
+- **Issue #39, #41**: Ready for PyPI release with all fixes from master branch
+
+---
+
+Updating builds to target 3.9.7
+
 2.1: Fixes merged to save modified IPTC info images
 
 1.9.5-8: https://bitbucket.org/gthomas/iptcinfo/issue/4/file-permissions-for-changed-files-are-not - copy original file's permission bits on save/saveAs

script.module.iptcinfo3/README.rst

@@ -1,7 +1,7 @@
 ``IPTCINFO 3``
 ==============
 
-`Build Status <https://travis-ci.org/crccheck/iptcinfo3.svg?branch=master>`_
+`Build Status <https://api.travis-ci.org/crccheck/iptcinfo3.png>`_
 
 Like IPTCInfo but finally compatible for Python 3
 -------------------------------------------------
@@ -47,6 +47,9 @@ Add/change an attribute
 ``info['caption/abstract'] = 'Witty caption here'``
 ``info['supplemental category'] = ['portrait']``
 
+Lists for keywords, so you can just append!
+``info['keywords']).append('cool')``
+
 Save new info to file
 ``info.save()``
 ``info.save_as('very_meta.jpg')``

script.module.iptcinfo3/addon.xml

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<addon id="script.module.iptcinfo3" name="IPTCInfo3" version="2.1.4+matrix.2" provider-name="Tamas Gulacsi, James Campbell">
+<addon id="script.module.iptcinfo3" name="IPTCInfo3" version="2.2.0" provider-name="Tamas Gulacsi, James Campbell">
 	<requires>
 		<import addon="xbmc.python" version="3.0.0"/>
 	</requires>

script.module.iptcinfo3/lib/iptcinfo3.py

@@ -11,7 +11,8 @@
 # All rights reserved.
 #
 # This program is free software; you can redistribute it and/or modify
-# it under the same terms as Python itself.
+# it under the terms of the Artistic License or the GNU General Public
+# License (GPL). You may choose either license.
 #
 # VERSION = '1.9';
 """
@@ -24,8 +25,9 @@
 import sys
 import tempfile
 from struct import pack, unpack
+import json
 
-__version__ = '2.1.4'
+__version__ = '2.2.0'
 __author__ = 'Gulácsi, Tamás'
 __updated_by__ = 'Campbell, James'
 
@@ -177,7 +179,7 @@ def jpeg_get_variable_length(fh):
 
     # Length includes itself, so must be at least 2
     if length < 2:
-        logger.warn("jpeg_get_variable_length: erroneous JPEG marker length")
+        logger.warning("jpeg_get_variable_length: erroneous JPEG marker length")
         return 0
     return length - 2
 
@@ -192,7 +194,7 @@ def jpeg_next_marker(fh):
     try:
         byte = read_exactly(fh, 1)
         while ord3(byte) != 0xff:
-            # logger.warn("jpeg_next_marker: bogus stuff in Jpeg file at: ')
+            # logger.warning("jpeg_next_marker: bogus stuff in Jpeg file at: ')
             byte = read_exactly(fh, 1)
 
         # Now skip any extra 0xffs, which are valid padding.
@@ -360,15 +362,15 @@ def jpeg_debug_scan(filename):  # pragma: no cover
                     break
 
                 if ord3(marker) == 0:
-                    logger.warn("Marker scan failed")
+                    logger.warning("Marker scan failed")
                     break
 
                 elif ord3(marker) == 0xd9:
                     logger.debug("Marker scan hit end of image marker")
                     break
 
                 if not jpeg_skip_variable(fh):
-                    logger.warn("jpeg_skip_variable failed")
+                    logger.warning("jpeg_skip_variable failed")
                     return None
 
 
@@ -480,7 +482,7 @@ def collect_adobe_parts(data):
     101: 'country/primary location name',
     103: 'original transmission reference',
     105: 'headline',
-    110: 'credit',
+    110: 'credit line',  # Updated from 'credit' to 'credit line' per IPTC Core 1.1
     115: 'source',
     116: 'copyright notice',
     118: 'contact',
@@ -536,6 +538,12 @@ def _key_as_int(cls, key):
             return key
         elif isinstance(key, str) and key.lower() in c_datasets_r:
             return c_datasets_r[key.lower()]
+        # Backward compatibility: 'credit' is now 'credit line' per IPTC Core 1.1
+        elif isinstance(key, str) and key.lower() == 'credit':
+            return 110
+        # Alias for compatibility with gThumb/exiftool
+        elif isinstance(key, str) and key.lower() == 'destination':
+            return 103  # Maps to 'original transmission reference'
         elif key.startswith(cls.c_cust_pre) and key[len(cls.c_cust_pre):].isdigit():
             # example: nonstandard_69 -> 69
             return int(key[len(cls.c_cust_pre):])
@@ -553,6 +561,13 @@ def _key_as_str(cls, key):
         else:
             raise KeyError("Key %s is not in %s!" % (key, list(c_datasets.keys())))
 
+    def __contains__(self, name):
+        try:
+            key = self._key_as_int(name)
+        except KeyError:
+            return False
+        return super().__contains__(key)
+
     def __getitem__(self, name):
         return self.get(self._key_as_int(name), None)
 
@@ -598,6 +613,7 @@ def __init__(self, fobj, force=False, inp_charset=None, out_charset=None):
             'contact': [],
         })
         self._fobj = fobj
+        self._force = force
         if duck_typed(fobj, 'read'):  # DELETEME
             self._filename = None
         else:
@@ -613,7 +629,7 @@ def __init__(self, fobj, force=False, inp_charset=None, out_charset=None):
                 if datafound:
                     self.collectIIMInfo(fh)
             else:
-                logger.warn('No IPTC data found in %s', fobj)
+                logger.warning('No IPTC data found in %s', fobj)
 
     def _filepos(self, fh):
         """For debugging, return what position in the file we are."""
@@ -630,7 +646,7 @@ def save_as(self, newfile, options=None):
         """Saves Jpeg with IPTC data to a given file name."""
         with smart_open(self._fobj, 'rb') as fh:
             if not file_is_jpeg(fh):
-                logger.error('Source file %s is not a Jpeg.' % self._fob)
+                logger.error('Source file %s is not a Jpeg.' % self._fobj)
                 return None
 
             jpeg_parts = jpeg_collect_file_parts(fh)
@@ -686,8 +702,10 @@ def save_as(self, newfile, options=None):
             os.unlink(tmpfn)
         else:
             tmpfh.close()
-            if os.path.exists(newfile):
-                shutil.move(newfile, newfile + '~')
+            if os.path.exists(newfile) and options is not None and 'overwrite' in options:
+                os.unlink(newfile)
+            elif os.path.exists(newfile):
+                shutil.move(newfile, "{file}~".format(file=newfile))
             shutil.move(tmpfn, newfile)
         return True
 
@@ -699,6 +717,9 @@ def __del__(self):
     def __len__(self):
         return len(self._data)
 
+    def __contains__(self, key):
+        return key in self._data
+
     def __getitem__(self, key):
         return self._data[key]
 
@@ -716,7 +737,7 @@ def scanToFirstIMMTag(self, fh):
             logger.info("File is JPEG, proceeding with JpegScan")
             return self.jpegScan(fh)
         else:
-            logger.warn("File not a JPEG, trying blindScan")
+            logger.warning("File not a JPEG, trying blindScan")
             return self.blindScan(fh)
 
     c_marker_err = {0: "Marker scan failed",
@@ -752,22 +773,26 @@ def jpegScan(self, fh):
                 err = "jpeg_skip_variable failed"
             if err is not None:
                 self.error = err
-                logger.warn(err)
+                # When force=True, log as INFO instead of WARNING since we expect no IPTC data
+                if self._force:
+                    logger.info(err)
+                else:
+                    logger.warning(err)
                 return None
 
         # If were's here, we must have found the right marker.
         # Now blindScan through the data.
         return self.blindScan(fh, MAX=jpeg_get_variable_length(fh))
 
-    def blindScan(self, fh, MAX=8192):
+    def blindScan(self, fh, MAX=819200):
         """Scans blindly to first IIM Record 2 tag in the file. This
         method may or may not work on any arbitrary file type, but it
         doesn't hurt to check. We expect to see this tag within the first
         8k of data. (This limit may need to be changed or eliminated
         depending on how other programs choose to store IIM.)"""
 
         offset = 0
-        # keep within first 8192 bytes
+        # keep within first 819200 bytes
         # NOTE: this may need to change
         logger.debug('blindScan: starting scan, max length %d', MAX)
 
@@ -776,7 +801,7 @@ def blindScan(self, fh, MAX=8192):
             try:
                 temp = read_exactly(fh, 1)
             except EOFException:
-                logger.warn("BlindScan: hit EOF while scanning")
+                logger.warning("BlindScan: hit EOF while scanning")
                 return None
             # look for tag identifier 0x1c
             if ord3(temp) == 0x1c:
@@ -787,15 +812,32 @@ def blindScan(self, fh, MAX=8192):
                     # found character set's record!
                     try:
                         temp = read_exactly(fh, jpeg_get_variable_length(fh))
-                        try:
-                            cs = unpack('!H', temp)[0]
-                        except Exception:  # TODO better exception
-                            #logger.warn('WARNING: problems with charset recognition (%r)', temp)
-                            cs = None
-                        if cs in c_charset:
-                            self.inp_charset = c_charset[cs]
-                        logger.info("BlindScan: found character set '%s' at offset %d",
-                                    self.inp_charset, offset)
+                        cs = None
+                        # Check for ISO 2022 escape sequence (starts with ESC 0x1b)
+                        if len(temp) >= 3 and ord3(temp[0]) == 0x1b:
+                            # Parse ISO 2022 escape sequences
+                            # ESC % G = UTF-8
+                            if temp == b'\x1b%G':
+                                self.inp_charset = 'utf_8'
+                            # ESC % / @ = UTF-16 (not commonly used)
+                            elif temp == b'\x1b%/@':
+                                self.inp_charset = 'utf_16'
+                            else:
+                                logger.debug(
+                                    "BlindScan: unknown ISO 2022 charset escape sequence %r",
+                                    temp)
+                        else:
+                            # Try legacy numeric charset encoding
+                            try:
+                                cs = unpack('!H', temp)[0]
+                                if cs in c_charset:
+                                    self.inp_charset = c_charset[cs]
+                            except Exception:
+                                logger.debug('BlindScan: could not parse charset from %r', temp)
+
+                        if self.inp_charset:
+                            logger.info("BlindScan: found character set '%s' at offset %d",
+                                        self.inp_charset, offset)
                     except EOFException:
                         pass
 
@@ -845,7 +887,7 @@ def collectIIMInfo(self, fh):
                 try:
                     value = str(value, encoding=self.inp_charset, errors='strict')
                 except Exception:  # TODO better exception
-                    logger.warn('Data "%r" is not in encoding %s!', value, self.inp_charset)
+                    logger.warning('Data "%r" is not in encoding %s!', value, self.inp_charset)
                     value = str(value, encoding=self.inp_charset, errors='replace')
 
             # try to extract first into _listdata (keywords, categories)
@@ -889,11 +931,22 @@ def packedIIMData(self):
         LOGDBG.debug('out=%s', hex_dump(out))
         # Iterate over data sets
         for dataset, value in self._data.items():
-            if len(value) == 0:
+            # Skip None, empty strings, empty lists, and NaN values
+            if value is None:
+                continue
+            # Handle float/int that might be NaN
+            if isinstance(value, (float, int)):
+                import math
+                if isinstance(value, float) and math.isnan(value):
+                    continue
+                # Convert numeric values to strings
+                value = str(value)
+            # Check length for strings and lists
+            if hasattr(value, '__len__') and len(value) == 0:
                 continue
 
             if not (isinstance(dataset, int) and dataset in c_datasets):
-                logger.warn("packedIIMData: illegal dataname '%s' (%d)", dataset, dataset)
+                logger.warning("packedIIMData: illegal dataname '%s' (%d)", dataset, dataset)
                 continue
 
             logger.debug('packedIIMData %02X: %r -> %r', dataset, value, self._enc(value))
@@ -944,7 +997,16 @@ def photoshopIIMBlock(self, otherparts, data):
 
 
 if __name__ == '__main__':  # pragma: no cover
-    logging.basicConfig(level=logging.DEBUG)
+    logging.basicConfig(level=logging.ERROR)
     if len(sys.argv) > 1:
         info = IPTCInfo(sys.argv[1])
-        print(info)
+        if info.__dict__ != '':
+            for k, v in info.__dict__.items():
+                if k == '_data':
+                    print(k)
+                    for key, value in v.items():
+                        if type(value) == list:
+                            print(key, [x.decode() for x in value])
+                            [print(x.decode()) for x in value]
+                        print(key, value)
+                print(k, v)