improve logging system

Author: URenko

comiclib/config.py

@@ -1,9 +1,13 @@
 from pydantic import BaseSettings
 from typing import Union
 import re
+import logging
+
+logger = logging.getLogger('ComicLib')
 
 class Settings(BaseSettings):
     debug: bool = False
+    loglevel: str = 'INFO'
     content: str = '.'
     thumb: str = './thumb'
     metadata: str = 'sqlite:///./comiclib_metadata.db'
@@ -16,7 +20,14 @@ class Settings(BaseSettings):
 settings = Settings()
 
 if settings.debug:
-    print(settings)
+    settings.loglevel = 'DEBUG'
+numeric_level = getattr(logging, settings.loglevel.upper(), None)
+if not isinstance(numeric_level, int):
+    raise ValueError(f'Invalid log level: {settings.loglevel}')
+logging.basicConfig(format='%(asctime)s %(levelname)-8s %(name)s: %(message)s',
+                    datefmt='%Y-%m-%d %H:%M:%S',
+                    level=numeric_level)
+logger.debug(settings)
 
 settings.UA_convert_jxl = re.compile(settings.UA_convert_jxl)
 settings.UA_convert_all = re.compile(settings.UA_convert_all)

comiclib/frontend_boost.py

@@ -2,6 +2,9 @@
 from pathlib import Path
 import requests
 
+import logging
+logger = logging.getLogger(__name__)
+
 dependencies = {
         '@fortawesome/fontawesome-free': '6.4.0',
         '@jcubic/tagger': '0.4.4',
@@ -73,11 +76,11 @@
 vendor_version = 0
 version_file = Path(__file__).parent / 'LANraragi/public/version'
 if not version_file.exists() or int(version_file.read_text()) < vendor_version:
-    print('Installing/updating front-end files...')
+    logger.info('Installing/updating front-end files...')
 
     s = requests.session()
     for name in dependencies:
-        print('downloading', name)
+        logger.info('downloading', name)
         r = s.get(f"https://registry.npmjs.com/{name}/-/{name.rpartition('/')[-1]}-{dependencies[name]}.tgz", allow_redirects=True)
         r.raise_for_status()
         with tarfile.open(fileobj=io.BytesIO(r.content), mode='r:gz') as t:

comiclib/scan.py

@@ -4,7 +4,10 @@
 import hashlib
 import time
 from pathlib import Path
-from pprint import pprint
+from pprint import pformat
+
+import logging
+logger = logging.getLogger(__name__)
 
 from .database import engine, Base, Archive, Tag, Category
 from sqlalchemy import select
@@ -26,7 +29,7 @@
 scanners = [(importlib.import_module('.scanner.'+name, __package__).Scanner(), name) for name in scanner.__all__] + \
           [(importlib.import_module(p.stem).Scanner(), p.stem) for p in Path('.').glob('*.py')]
 scanners.sort(key=lambda t:t[1])
-print("Loaded scanners:", [scanner[1] for scanner in scanners])
+logger.info(f"Loaded scanners: {[scanner[1] for scanner in scanners]}")
 
 
 def scan(paths):
@@ -60,7 +63,7 @@ def scan(paths):
                 continue
             if not any(tag.startswith("date_added:") for tag in metadata["tags"]):
                 metadata["tags"].add(f"date_added:{int(real_path.stat().st_mtime)}")
-            pprint(metadata)
+            logging.debug(pformat(metadata))
             a.title = metadata["title"]
             a.subtitle = metadata["subtitle"]
             a.source = metadata["source"]
@@ -105,8 +108,7 @@ def watch():
                         time.sleep(1)
                     scan([fname])
             except Exception as err:
-                if settings.debug:
-                    print(err)
+                logger.error(err)
 
 
 def scannow():

comiclib/scanner/10-zip.py

@@ -2,13 +2,15 @@
 
 from zipfile import ZipFile
 
+import logging
+logger = logging.getLogger(__name__)
 
 class Scanner:
     '''Handle regular zip files, with the filename as the title.'''
 
     def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) -> bool:
         if path.match('**/*.zip') and not path.is_dir():
-            print(f' -> zip.py get {path}')
+            logger.info(f' <- {path}')
             metadata["title"] = path.stem
             with ZipFile(path) as z:
                 metadata["pagecount"] = len(

comiclib/scanner/20-ccloli.py

@@ -1,6 +1,8 @@
 from pathlib import Path
 from zipfile import ZipFile
 
+import logging
+logger = logging.getLogger(__name__)
 
 try:
     from charset_normalizer import from_bytes
@@ -24,7 +26,7 @@ def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) ->
                 info = z_comments
             else:
                 return False
-            print(f' -> ccloli get {path}')
+            logger.info(f' <- {path}')
             if "hentai.org" not in info[2]: return False
             metadata["title"] = info[0]
             metadata["subtitle"] = info[1]

comiclib/scanner/21-hath.py

@@ -1,13 +1,15 @@
 from pathlib import Path
 import re
 
+import logging
+logger = logging.getLogger(__name__)
 
 class Scanner:
     '''For archives downloaded via Hentai@Home'''
 
     def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) -> bool:
         if path.is_dir() and (path / 'galleryinfo.txt').exists():
-            print(f' -> hath.py get {path}')
+            logger.info(f' <- {path}')
             metadata["source"] = 'https://exhentai.org/g/' + re.search(r"\[(\d+)\]$", path.name)[1] + '/'
             information = (path / 'galleryinfo.txt').read_text().splitlines()
             _key, _, title = information[0].partition(':')

comiclib/scanner/30-importEHdb.py

@@ -10,6 +10,8 @@ class Settings(BaseSettings):
     importEHdb_matchtorrent: bool = True
 settings = Settings()
 
+import logging
+logger = logging.getLogger(__name__)
 
 def blur_title(title: str):
     if not isinstance(title, str):
@@ -34,7 +36,7 @@ class Scanner:
 
     def __init__(self) -> None:
         if Path("api_dump.sqlite").exists():
-            print('Loading ehentai metadata database, please wait...')
+            logger.info('Loading ehentai metadata database, please wait...')
             self.con = sqlite3.connect("api_dump.sqlite", check_same_thread=False)
             if settings.importEHdb_matchtitle:
                 self.db_title = {blur_title(row[0]): row[1] for row in self.con.execute("SELECT title, gid FROM gallery") if not row[0] is None}
@@ -47,7 +49,7 @@ def __init__(self) -> None:
                         if torrent['name'] is None: continue
                         self.db_title_torrent[blur_title(Path(torrent['name']).stem)] = gid
             self.con.row_factory = dict_factory
-            print('Loaded.')
+            logger.info('Loaded.')
         else:
             self.con = None
 
@@ -72,7 +74,7 @@ def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) ->
         if self.con is None:
             return False
         elif prev_scanners and not (gid := self.get_gid(metadata)) is None:
-            print(f' -> importEHdb get {path}')
+            logger.info(f' <- {path}')
             res = self.con.execute("SELECT title, title_jpn, category, posted, thumb, artist, `group`, parody, character, female, male, language, mixed, other, cosplayer, rest FROM gallery WHERE gid == ?", (gid,)).fetchone()
             if res is None: return False
             metadata["title"] = res.pop("title")

comiclib/scanner/40-thumb.py

@@ -1,13 +1,16 @@
 from pathlib import Path
 from ..utils import extract_thumbnail
 
+import logging
+logger = logging.getLogger(__name__)
+
 class Scanner:
     '''Generate thumbnails from files.'''
 
     def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) -> bool:
         if not prev_scanners or not metadata.get('thumb') is None:
             return False
-        print(f' -> thumb.py get {path}')
+        logger.info(f' <- {path}')
         thumb = extract_thumbnail(path, id, 1)
         metadata['thumb'] = str(thumb)
         return True

docs/en/docs/settings.md

@@ -27,6 +27,7 @@ The following is a list of available settings:
 | Environment variable | Description | Default value |
 | ------- | ---- | ----- |
 | `debug` | Turn on debug output (`True`/`False`) | `False` |
+| `loglevel` | Log level (`DEBUG`/`INFO`/`WARNING`/`ERROR`/`CRITICAL`). If `debug` is `True`, it will be overwritten to `DEBUG` | `INFO` |
 | `content` | The path where the comic file is stored (due to [a problem with Python](https://github.com/python/cpython/issues/77609), following symbolic links is not currently supported) | `.` |
 | `thumb` | The path where the generated thumbnails are stored | `./thumb`|
 | `metadata` | The URL for metadata database, refer to [SQLAlchemy documentation](https://docs.sqlalchemy.org/en/20/core/engines.html#database-urls) | `sqlite:///./comiclib_metadata.db` |

docs/zh/docs/settings.md

@@ -27,6 +27,7 @@
 | 环境变量 | 说明 | 默认值 |
 | ------- | ---- | ----- |
 | `debug` | 开启调试输出（`True`/`False`） | `False` |
+| `loglevel` | 日志级别（`DEBUG`/`INFO`/`WARNING`/`ERROR`/`CRITICAL`），若`debug`为`True`，会被覆盖为`DEBUG` | `INFO` |
 | `content` | 漫画文件存放的路径（由于 [Python 的一个问题](https://github.com/python/cpython/issues/77609)，暂不支持跟随符号链接） | `.` |
 | `thumb` | 生成的缩略图存放的路径 | `./thumb`|
 | `metadata` | 元数据库 URL，参考[SQLAlchemy 文档](https://docs.sqlalchemy.org/en/20/core/engines.html#database-urls) | `sqlite:///./comiclib_metadata.db` |