Fix for newlines in exif tags, #513

This commit is contained in:
Rhet Turnbull
2021-08-29 12:18:20 -07:00
parent 8e2b768236
commit f0d7496bc6
7 changed files with 131 additions and 38 deletions

View File

@@ -1702,7 +1702,7 @@ Substitution Description
{lf} A line feed: '\n', alias for {newline}
{cr} A carriage return: '\r'
{crlf} a carriage return + line feed: '\r\n'
{osxphotos_version} The osxphotos version, e.g. '0.42.77'
{osxphotos_version} The osxphotos version, e.g. '0.42.78'
{osxphotos_cmd_line} The full command line used to run osxphotos
The following substitutions may result in multiple values. Thus if specified for
@@ -3561,7 +3561,7 @@ The following template field substitutions are availabe for use the templating s
|{lf}|A line feed: '\n', alias for {newline}|
|{cr}|A carriage return: '\r'|
|{crlf}|a carriage return + line feed: '\r\n'|
|{osxphotos_version}|The osxphotos version, e.g. '0.42.77'|
|{osxphotos_version}|The osxphotos version, e.g. '0.42.78'|
|{osxphotos_cmd_line}|The full command line used to run osxphotos|
|{album}|Album(s) photo is contained in|
|{folder_album}|Folder path + album photo is contained in. e.g. 'Folder/Subfolder/Album' or just 'Album' if no enclosing folder|

View File

@@ -1,3 +1,3 @@
""" version info """
__version__ = "0.42.77"
__version__ = "0.42.78"

View File

@@ -7,6 +7,7 @@
pyexiftool: https://github.com/smarnach/pyexiftool which provides more functionality """
import atexit
import html
import json
import logging
import os
@@ -24,6 +25,24 @@ EXIFTOOL_STAYOPEN_EOF_LEN = len(EXIFTOOL_STAYOPEN_EOF)
EXIFTOOL_PROCESSES = []
def escape_str(s):
"""escape string for use with exiftool -E"""
if type(s) != str:
return s
s = html.escape(s)
s = s.replace("\n", "
")
s = s.replace("\t", "	")
s = s.replace("\r", "
")
return s
def unescape_str(s):
"""unescape an HTML string returned by exiftool -E"""
if type(s) != str:
return s
return html.unescape(s)
@atexit.register
def terminate_exiftool():
"""Terminate any running ExifTool subprocesses; call this to cleanup when done using ExifTool"""
@@ -110,6 +129,7 @@ class _ExifToolProc:
"-n", # no print conversion (e.g. print tag values in machine readable format)
"-P", # Preserve file modification date/time
"-G", # print group name for each tag
"-E", # escape tag values for HTML (allows use of HTML 
 for newlines)
],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
@@ -189,6 +209,7 @@ class ExifTool:
if value is None:
value = ""
value = escape_str(value)
command = [f"-{tag}={value}"]
if self.overwrite and not self._context_mgr:
command.append("-overwrite_original")
@@ -233,6 +254,7 @@ class ExifTool:
for value in values:
if value is None:
raise ValueError("Can't add None value to tag")
value = escape_str(value)
command.append(f"-{tag}+={value}")
if self.overwrite and not self._context_mgr:
@@ -335,6 +357,7 @@ class ExifTool:
json_str, _, _ = self.run_commands("-json")
if not json_str:
return dict()
json_str = unescape_str(json_str.decode("utf-8"))
try:
exifdict = json.loads(json_str)
@@ -342,7 +365,6 @@ class ExifTool:
# will fail with some commands, e.g --ext AVI which produces
# 'No file with specified extension' instead of json
return dict()
exifdict = exifdict[0]
if not tag_groups:
# strip tag groups
@@ -360,6 +382,7 @@ class ExifTool:
def json(self):
"""returns JSON string containing all EXIF tags and values from exiftool"""
json, _, _ = self.run_commands("-json")
json = unescape_str(json.decode("utf-8"))
return json
def _read_exif(self):
@@ -451,4 +474,3 @@ class _ExifToolCaching(ExifTool):
"""Clear cached data so that calls to json or asdict return fresh data"""
self._json_cache = None
self._asdict_cache = {}

View File

@@ -1871,12 +1871,6 @@ def _exiftool_dict(
self.date_modified
).strftime("%Y:%m:%d %H:%M:%S")
# remove any new lines in any fields
for field, val in exif.items():
if type(val) == str:
exif[field] = val.replace("\n", " ")
elif type(val) == list:
exif[field] = [str(v).replace("\n", " ") for v in val if v is not None]
return exif

View File

@@ -1376,12 +1376,12 @@ def test_no_adjustments(photosdb):
def test_exiftool_newlines_in_description(photosdb):
"""Test that exiftool code removes newlines embedded in description, issue #393"""
"""Test that exiftool handles newlines embedded in description, issue #393"""
photo = photosdb.get_photo(UUID_DICT["description_newlines"])
exif = photo._exiftool_dict()
assert photo.description.find("\n") > 0
assert exif["EXIF:ImageDescription"].find("\n") == -1
assert exif["EXIF:ImageDescription"].find("\n") > 0
@pytest.mark.skip(SKIP_TEST, reason="Not yet implemented")

View File

@@ -141,6 +141,44 @@ def test_setvalue_1():
assert exif.data["IPTC:Keywords"] == "test"
def test_setvalue_multiline():
# test setting a tag value with embedded newline
import os.path
import tempfile
import osxphotos.exiftool
from osxphotos.fileutil import FileUtil
tempdir = tempfile.TemporaryDirectory(prefix="osxphotos_")
tempfile = os.path.join(tempdir.name, os.path.basename(TEST_FILE_ONE_KEYWORD))
FileUtil.copy(TEST_FILE_ONE_KEYWORD, tempfile)
exif = osxphotos.exiftool.ExifTool(tempfile)
exif.setvalue("EXIF:ImageDescription", "multi\nline")
assert not exif.error
exif._read_exif()
assert exif.data["EXIF:ImageDescription"] == "multi\nline"
def test_setvalue_non_alphanumeric_chars():
# test setting a tag value non-alphanumeric characters
import os.path
import tempfile
import osxphotos.exiftool
from osxphotos.fileutil import FileUtil
tempdir = tempfile.TemporaryDirectory(prefix="osxphotos_")
tempfile = os.path.join(tempdir.name, os.path.basename(TEST_FILE_ONE_KEYWORD))
FileUtil.copy(TEST_FILE_ONE_KEYWORD, tempfile)
exif = osxphotos.exiftool.ExifTool(tempfile)
exif.setvalue("EXIF:ImageDescription", "<hello>{world}$bye#foo%bar")
assert not exif.error
exif._read_exif()
assert exif.data["EXIF:ImageDescription"] == "<hello>{world}$bye#foo%bar"
def test_setvalue_warning():
# test setting illegal tag value generates warning
import os.path
@@ -311,6 +349,45 @@ def test_addvalues_2():
assert sorted(exif.data["IPTC:Keywords"]) == sorted(test_multi)
def test_addvalues_non_alphanumeric_multiline():
# test setting a tag value
import os.path
import tempfile
import osxphotos.exiftool
from osxphotos.fileutil import FileUtil
tempdir = tempfile.TemporaryDirectory(prefix="osxphotos_")
tempfile = os.path.join(tempdir.name, os.path.basename(TEST_FILE_ONE_KEYWORD))
FileUtil.copy(TEST_FILE_ONE_KEYWORD, tempfile)
exif = osxphotos.exiftool.ExifTool(tempfile)
exif.addvalues("IPTC:Keywords", "multi\nline", "<Foo>\t{bar}")
assert not exif.error
exif._read_exif()
assert sorted(exif.data["IPTC:Keywords"]) == sorted(
["wedding", "multi\nline", "<Foo>\t{bar}"]
)
def test_addvalues_unicode():
# test setting a tag value with unicode
import os.path
import tempfile
import osxphotos.exiftool
from osxphotos.fileutil import FileUtil
tempdir = tempfile.TemporaryDirectory(prefix="osxphotos_")
tempfile = os.path.join(tempdir.name, os.path.basename(TEST_FILE_ONE_KEYWORD))
FileUtil.copy(TEST_FILE_ONE_KEYWORD, tempfile)
exif = osxphotos.exiftool.ExifTool(tempfile)
exif.setvalue("IPTC:Keywords", None)
exif.addvalues("IPTC:Keywords", "ǂ", "Ƕ")
assert not exif.error
exif._read_exif()
assert sorted(exif.data["IPTC:Keywords"]) == sorted(["ǂ", "Ƕ"])
def test_singleton():
import osxphotos.exiftool

View File

@@ -1346,12 +1346,12 @@ def test_no_adjustments(photosdb):
def test_exiftool_newlines_in_description(photosdb):
"""Test that exiftool code removes newlines embedded in description, issue #393"""
"""Test that exiftool handles newlines embedded in description, issue #393"""
photo = photosdb.get_photo(UUID_DICT["description_newlines"])
exif = photo._exiftool_dict()
assert photo.description.find("\n") > 0
assert exif["EXIF:ImageDescription"].find("\n") == -1
assert exif["EXIF:ImageDescription"].find("\n") > 0
@pytest.mark.skip(SKIP_TEST, reason="Not yet implemented")