Skip to content

use resolve book path to get full path to book before running extract #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lpukatch wants to merge 1 commit into
base: main
Choose a base branch
from
Open

use resolve book path to get full path to book before running extract #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions src/ebook_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ def __init__(self, books_dir):
self.hash_method = os.getenv("KOSYNC_HASH_METHOD", "content").lower()
logger.info(f"Initialized EbookParser. ID Method: {self.hash_method}")

def _resolve_book_path(self, filename):
def resolve_book_path(self, filename):
"""
Robustly finds a file in the books directory, handling special characters
like [ ] (brackets) which break standard glob patterns.
Expand Down Expand Up @@ -164,7 +164,7 @@ def _normalize(self, text):
def find_text_location(self, filename, search_phrase):
try:
# FIXED: Use the new robust path resolver
book_path = self._resolve_book_path(filename)
book_path = self.resolve_book_path(filename)

full_text, spine_map = self.extract_text_and_map(book_path)

Expand Down Expand Up @@ -269,7 +269,7 @@ def find_text_location(self, filename, search_phrase):
def get_text_at_percentage(self, filename, percentage):
try:
# FIXED: Use the new robust path resolver
book_path = self._resolve_book_path(filename)
book_path = self.resolve_book_path(filename)

full_text, _ = self.extract_text_and_map(book_path)

Expand All @@ -291,7 +291,7 @@ def get_text_at_percentage(self, filename, percentage):

def get_character_delta(self, filename, percentage_prev, percentage_new):
try:
book_path = self._resolve_book_path(filename)
book_path = self.resolve_book_path(filename)

full_text, _ = self.extract_text_and_map(book_path)

Expand Down
3 changes: 2 additions & 1 deletion src/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,8 @@ def check_pending_jobs(self):
transcript_path = self.transcriber.process_audio(mapping['abs_id'], audio_files)

logger.info(" Priming ebook cache...")
self.ebook_parser.extract_text_and_map(mapping['ebook_filename'])
book_path = self.ebook_parser.resolve_book_path(mapping['ebook_filename'])
self.ebook_parser.extract_text_and_map(book_path)

mapping['transcript_file'] = str(transcript_path)
mapping['status'] = 'active'
Expand Down