chore: logger should not be setting up a BasicConfig (#106)

* feat: simple logger

* doc: changelog and version

Author: yuming-long

Diff for: CHANGELOG.md

@@ -1,5 +1,6 @@
-## 0.3.3-dev1
+## 0.3.3-dev2
 
+* Removes BasicConfig from logger configuration
 * Adds the `partition_email` partitioning brick
 * Adds the `replace_mime_encodings` cleaning bricks
 * Small fix to HTML parsing related to processing list items with sub-tags

Diff for: test_unstructured/test_logger.py

@@ -1 +1 @@
-__version__ = "0.3.3-dev1"  # pragma: no cover
+__version__ = "0.3.3-dev2"  # pragma: no cover

Diff for: unstructured/__version__.py

@@ -9,7 +9,7 @@
 
 from lxml import etree
 
-from unstructured.logger import get_logger
+from unstructured.logger import logger
 
 from unstructured.cleaners.core import clean_bullets, replace_unicode_quotes
 from unstructured.documents.base import Page
@@ -21,8 +21,6 @@
     is_possible_title,
 )
 
-logger = get_logger()
-
 TEXT_TAGS: Final[List[str]] = ["p", "a", "td", "span", "font"]
 LIST_ITEM_TAGS: Final[List[str]] = ["li", "dd"]
 HEADING_TAGS: Final[List[str]] = ["h1", "h2", "h3", "h4", "h5", "h6"]

Diff for: unstructured/documents/html.py

@@ -2,10 +2,9 @@
 
 import lxml.etree as etree
 
-from unstructured.logger import get_logger
+from unstructured.logger import logger
 from unstructured.documents.base import Document, Page
 
-logger = get_logger()
 
 VALID_PARSERS = Union[etree.HTMLParser, etree.XMLParser, None]
 

Diff for: unstructured/documents/xml.py

@@ -1,20 +1,3 @@
 import logging
-import os
-import sys
 
-if sys.version_info < (3, 8):
-    from typing_extensions import Final
-else:
-    from typing import Final
-
-DEFAULT_LOG_LEVEL: Final[str] = "WARNING"
-
-logging.basicConfig(format="%(asctime)s [%(levelname)s]: %(message)s")
-
-
-def get_logger() -> logging.Logger:
-    log_level = os.environ.get("LOG_LEVEL", DEFAULT_LOG_LEVEL).upper()
-    log_level = DEFAULT_LOG_LEVEL if not log_level else log_level
-    logger = logging.getLogger(__name__)
-    logger.setLevel(level=log_level)
-    return logger
+logger = logging.getLogger("unstructured")

Diff for: unstructured/logger.py

@@ -9,9 +9,8 @@
 from unstructured.cleaners.core import remove_punctuation
 from unstructured.nlp.patterns import UNICODE_BULLETS_RE
 from unstructured.nlp.tokenize import pos_tag, sent_tokenize, word_tokenize
-from unstructured.logger import get_logger
+from unstructured.logger import logger
 
-logger = get_logger()
 
 POS_VERB_TAGS: Final[List[str]] = ["VB", "VBG", "VBD", "VBN", "VBP", "VBZ"]