v0.2.2 resolve emoji issue in file names
This commit is contained in:
Ben
@@ -1,8 +1,23 @@
|
||||
# File: /home/code/projects/manga-organizer-1/cbz-volume-combiner/cbz_volume_combiner/file_utils.py
|
||||
import os
|
||||
import re
|
||||
import unicodedata
|
||||
from .parsing import parse_manga_filename
|
||||
|
||||
def is_emoji(char):
|
||||
"""Check if a character is an emoji or other problematic symbol."""
|
||||
return (
|
||||
unicodedata.category(char) in ('So', 'Sm') or # Symbol categories
|
||||
ord(char) > 0x1F000 # Emoji range
|
||||
)
|
||||
|
||||
def has_problematic_characters(filename):
|
||||
"""Check if filename contains emoji or problematic characters."""
|
||||
basename = os.path.basename(filename)
|
||||
for char in basename:
|
||||
if is_emoji(char) or char == '?':
|
||||
return True, char
|
||||
return False, None
|
||||
|
||||
def find_cbz_files(folder_path, recursive=False, extra_verbose=False):
|
||||
"""Find all CBZ files in the given folder."""
|
||||
cbz_files = []
|
||||
@@ -39,87 +54,118 @@ def fix_missing_files(chapter_infos, folder_path, extra_verbose=False):
|
||||
fixed_chapters.append(chapter_info)
|
||||
continue
|
||||
|
||||
# If we're here, the file doesn't exist - get the problematic filename
|
||||
base_filename = os.path.basename(chapter_info['filename'])
|
||||
# If file doesn't exist, look for it by volume and chapter
|
||||
directory = os.path.dirname(chapter_info['filename'])
|
||||
vol_num = chapter_info['volume']
|
||||
chap_num = chapter_info['chapter_str']
|
||||
|
||||
if extra_verbose:
|
||||
print(f"Trying to find replacement for: {base_filename}")
|
||||
print(f"Looking for alternative for {os.path.basename(chapter_info['filename'])}")
|
||||
|
||||
# First approach: Direct check with normalized path
|
||||
# This is for cases where Python's path handling might be different from the filesystem
|
||||
found_replacement = False
|
||||
# Find file by volume and chapter numbers directly
|
||||
actual_file = find_file_by_volume_chapter(directory, vol_num, chap_num, extra_verbose)
|
||||
|
||||
# Look for similar files in the directory
|
||||
try:
|
||||
# Get all CBZ files in the directory
|
||||
cbz_files_in_dir = [f for f in os.listdir(directory) if f.lower().endswith('.cbz')]
|
||||
|
||||
# First try: Look for exact matches with volume and chapter numbers
|
||||
vol_num = chapter_info['volume']
|
||||
chap_num = chapter_info['chapter_str']
|
||||
|
||||
# Improved pattern matching for volume and chapter numbers
|
||||
vol_pattern = f"v{vol_num:02d}" # e.g., "v07"
|
||||
chap_pattern = f"c{chap_num}" # e.g., "c037"
|
||||
|
||||
# Try to find a direct match first
|
||||
for file in cbz_files_in_dir:
|
||||
# Check volume and chapter patterns
|
||||
if vol_pattern in file and chap_pattern in file:
|
||||
potential_path = os.path.join(directory, file)
|
||||
if os.path.exists(potential_path):
|
||||
if extra_verbose:
|
||||
print(f" Found direct match: {file}")
|
||||
new_chapter_info = dict(chapter_info)
|
||||
new_chapter_info['filename'] = potential_path
|
||||
fixed_chapters.append(new_chapter_info)
|
||||
found_replacement = True
|
||||
break
|
||||
|
||||
# If no direct match, try more flexible matching
|
||||
if not found_replacement:
|
||||
# Fuzzy match approach
|
||||
chapter_pattern = rf"v0*{vol_num}\s+c0*{chap_num.lstrip('0')}"
|
||||
|
||||
for file in cbz_files_in_dir:
|
||||
# Remove special characters for comparison
|
||||
clean_file = file
|
||||
for char in "'?,":
|
||||
clean_file = clean_file.replace(char, '')
|
||||
|
||||
# Strip special characters from the pattern too
|
||||
clean_pattern = chapter_pattern
|
||||
for char in "'?,":
|
||||
clean_pattern = clean_pattern.replace(char, '')
|
||||
|
||||
# Try matching with cleaned strings
|
||||
if re.search(chapter_pattern, file, re.IGNORECASE) or re.search(clean_pattern, clean_file, re.IGNORECASE):
|
||||
potential_path = os.path.join(directory, file)
|
||||
if os.path.exists(potential_path):
|
||||
if extra_verbose:
|
||||
print(f" Found fuzzy match: {file}")
|
||||
new_chapter_info = dict(chapter_info)
|
||||
new_chapter_info['filename'] = potential_path
|
||||
fixed_chapters.append(new_chapter_info)
|
||||
found_replacement = True
|
||||
break
|
||||
|
||||
# Last resort: List all files and let the user see what's available
|
||||
if not found_replacement and extra_verbose:
|
||||
print(" No match found. Available files in directory:")
|
||||
for idx, file in enumerate(sorted(cbz_files_in_dir)):
|
||||
if idx < 20: # Limit to first 20 files to avoid spam
|
||||
print(f" - {file}")
|
||||
else:
|
||||
print(f" ... and {len(cbz_files_in_dir) - 20} more files")
|
||||
break
|
||||
|
||||
except Exception as e:
|
||||
if actual_file and os.path.exists(actual_file):
|
||||
if extra_verbose:
|
||||
print(f" Error while searching for replacement: {str(e)}")
|
||||
print(f"Found alternative file: {os.path.basename(actual_file)}")
|
||||
|
||||
if not found_replacement:
|
||||
new_chapter_info = dict(chapter_info)
|
||||
new_chapter_info['filename'] = actual_file
|
||||
fixed_chapters.append(new_chapter_info)
|
||||
else:
|
||||
if extra_verbose:
|
||||
print(f"No alternative found for volume {vol_num}, chapter {chap_num}")
|
||||
unresolved_chapters.append(chapter_info)
|
||||
|
||||
return fixed_chapters, unresolved_chapters
|
||||
return fixed_chapters, unresolved_chapters
|
||||
|
||||
def find_file_by_volume_chapter(directory, volume_num, chapter_num, extra_verbose=False):
|
||||
"""Find a file in a directory by its volume and chapter number only."""
|
||||
if not os.path.exists(directory):
|
||||
if extra_verbose:
|
||||
print(f"Directory does not exist: {directory}")
|
||||
return None
|
||||
|
||||
if extra_verbose:
|
||||
print(f"Looking for volume {volume_num}, chapter {chapter_num} in {directory}")
|
||||
|
||||
try:
|
||||
files = [f for f in os.listdir(directory) if f.lower().endswith('.cbz')]
|
||||
|
||||
# We'll only focus on the essential part: finding files by volume and chapter numbers
|
||||
# regardless of special characters or encoding issues
|
||||
|
||||
# First: Look for exact pattern matches
|
||||
for file in files:
|
||||
# Look for both zero-padded and non-zero-padded versions
|
||||
v_patterns = [f"v{volume_num:02d}", f"v{volume_num}"]
|
||||
c_patterns = [f"c{chapter_num}", f"c{chapter_num.zfill(3)}" if chapter_num.isdigit() else f"c{chapter_num}"]
|
||||
|
||||
for v_pattern in v_patterns:
|
||||
for c_pattern in c_patterns:
|
||||
if v_pattern in file and c_pattern in file:
|
||||
if extra_verbose:
|
||||
print(f"Found exact match: {file}")
|
||||
return os.path.join(directory, file)
|
||||
|
||||
# Second: Use regex pattern matching
|
||||
for file in files:
|
||||
v_match = re.search(fr'v0*{volume_num}[^0-9]', file.lower())
|
||||
c_match = re.search(fr'c0*{chapter_num}[^0-9]', file.lower())
|
||||
|
||||
if v_match and c_match:
|
||||
if extra_verbose:
|
||||
print(f"Found regex match: {file}")
|
||||
return os.path.join(directory, file)
|
||||
|
||||
# Third: Last resort - simplified alphanumeric comparison
|
||||
for file in files:
|
||||
clean_file = ''.join(c.lower() for c in file if c.isalnum())
|
||||
if f"v{volume_num}" in clean_file and f"c{chapter_num}" in clean_file:
|
||||
if extra_verbose:
|
||||
print(f"Found simplified match: {file}")
|
||||
return os.path.join(directory, file)
|
||||
|
||||
if extra_verbose:
|
||||
print(f"No match found for volume {volume_num}, chapter {chapter_num}")
|
||||
print("Available files:")
|
||||
for file in sorted(files)[:10]:
|
||||
print(f" - {file}")
|
||||
if len(files) > 10:
|
||||
print(f" ... and {len(files) - 10} more")
|
||||
|
||||
return None
|
||||
except Exception as e:
|
||||
if extra_verbose:
|
||||
print(f"Error searching for file: {e}")
|
||||
return None
|
||||
|
||||
def create_clean_filename_mapping(cbz_files, extra_verbose=False):
|
||||
"""Create a mapping of problematic filenames to clean alternatives."""
|
||||
filename_mapping = {}
|
||||
|
||||
for file_path in cbz_files:
|
||||
has_problem, _ = has_problematic_characters(file_path)
|
||||
|
||||
if has_problem:
|
||||
# Get the directory and filename
|
||||
directory = os.path.dirname(file_path)
|
||||
filename = os.path.basename(file_path)
|
||||
|
||||
# Create a clean version of the filename by removing problematic characters
|
||||
clean_filename = ''.join(c if not is_emoji(c) and c != '?' else '_' for c in filename)
|
||||
|
||||
# Make sure we don't create duplicates
|
||||
base, ext = os.path.splitext(clean_filename)
|
||||
counter = 1
|
||||
while os.path.exists(os.path.join(directory, clean_filename)):
|
||||
clean_filename = f"{base}_{counter}{ext}"
|
||||
counter += 1
|
||||
|
||||
# Add to mapping
|
||||
filename_mapping[file_path] = os.path.join(directory, clean_filename)
|
||||
|
||||
if extra_verbose:
|
||||
print(f"Mapped: {filename} -> {clean_filename}")
|
||||
|
||||
return filename_mapping
|
||||
Reference in New Issue
Block a user