feat: replace debug parameter with Python logging (DEBUG)

The 'debug' parameter was deprecated and will be removed in a future release. We've switched to using Python's built-in logging module with the DEBUG level.
danielnsilva · Jun 1, 2024 · d5bfa38 · d5bfa38
1 parent 53015d2
commit d5bfa38
Show file tree

Hide file tree

Showing 5 changed files with 59 additions and 72 deletions.
diff --git a/semanticscholar/ApiRequester.py b/semanticscholar/ApiRequester.py
@@ -1,27 +1,31 @@
+import asyncio
+import json
+import logging
+import warnings
 from typing import List, Union
 
 import httpx
-import asyncio
-import warnings
-import json
-from tenacity import (retry as rerun, retry_if_exception_type,
-                      stop_after_attempt, wait_fixed)
+from tenacity import retry as rerun
+from tenacity import retry_if_exception_type, stop_after_attempt, wait_fixed
+
+from semanticscholar.SemanticScholarException import (
+    BadQueryParametersException, ObjectNotFoundException)
 
 from semanticscholar.SemanticScholarException import \
     BadQueryParametersException, ObjectNotFoundException
 
+logger = logging.getLogger('semanticscholar')
+
 
 class ApiRequester:
 
-    def __init__(self, timeout, debug, retry: bool = True) -> None:
+    def __init__(self, timeout, retry: bool = True) -> None:
         '''
         :param float timeout: an exception is raised \
             if the server has not issued a response for timeout seconds.
-        :param bool debug: enable debug mode.
         :param bool retry: enable retry mode.
         '''
         self.timeout = timeout
-        self.debug = debug
         self.retry = retry
 
     @property
@@ -38,20 +42,6 @@ def timeout(self, timeout: int) -> None:
         '''
         self._timeout = timeout
 
-    @property
-    def debug(self) -> bool:
-        '''
-        :type: :class:`bool`
-        '''
-        return self._debug
-
-    @debug.setter
-    def debug(self, debug: bool) -> None:
-        '''
-        :param bool debug:
-        '''
-        self._debug = debug
-
     @property
     def retry(self) -> bool:
         '''
@@ -81,15 +71,6 @@ def _curl_cmd(
         curl_cmd += f' {url}'
         return curl_cmd
 
-    def _print_debug(self, url, headers, payload, method) -> None:
-        print('-' * 80)
-        print(f'Method: {method}\n')
-        print(f'URL:\n{url}\n')
-        print(f'Headers:\n{headers}\n')
-        print(f'Payload:\n{payload}\n')
-        print(f'cURL command:\n{self._curl_cmd(url, method, headers, payload)}')
-        print('-' * 80)
-
     async def get_data_async(
         self,
         url: str,
@@ -129,8 +110,10 @@ async def _get_data_async(
         url = f'{url}?{parameters.lstrip("&")}'
         method = 'POST' if payload else 'GET'
 
-        if self.debug:
-            self._print_debug(url, headers, payload, method)
+        logger.debug(f'HTTP Request: {method} {url}')
+        logger.debug(f'Headers: {headers}')
+        logger.debug(f'Payload: {payload}')
+        logger.debug(f'cURL command: {self._curl_cmd(url, method, headers, payload)}')
 
         async with httpx.AsyncClient() as client:
             r = await client.request(

diff --git a/semanticscholar/AsyncSemanticScholar.py b/semanticscholar/AsyncSemanticScholar.py
@@ -1,6 +1,7 @@
+import logging
 import re
-from typing import List, Literal, Tuple, Union
 import warnings
+from typing import List, Literal, Tuple, Union
 
 from semanticscholar.ApiRequester import ApiRequester
 from semanticscholar.Author import Author
@@ -10,6 +11,8 @@
 from semanticscholar.Paper import Paper
 from semanticscholar.Reference import Reference
 
+logger = logging.getLogger('semanticscholar')
+
 
 class AsyncSemanticScholar:
     '''
@@ -40,6 +43,12 @@ def __init__(
         :param bool retry: enable retry mode.
         '''
 
+        if debug:
+            warnings.warn(
+                'The debug parameter is deprecated and will be removed in a \
+                future release. Use Python\'s standard logging in DEBUG level \
+                instead.')
+
         if api_url:
             self.api_url = api_url
         else:
@@ -49,9 +58,9 @@ def __init__(
             self.auth_header = {'x-api-key': api_key}
 
         self._timeout = timeout
-        self._debug = debug
         self._retry = retry
-        self._requester = ApiRequester(self._timeout, self._debug, self._retry)
+        self._requester = ApiRequester(self._timeout, self._retry)
+        self.debug = debug
 
     @property
     def timeout(self) -> int:
@@ -81,7 +90,10 @@ def debug(self, debug: bool) -> None:
         :param bool debug:
         '''
         self._debug = debug
-        self._requester.debug = debug
+        if self._debug:
+            logging.basicConfig(level=logging.DEBUG)
+        else:
+            logging.basicConfig(level=logging.WARNING)
 
     @property
     def retry(self) -> bool:
@@ -190,7 +202,7 @@ async def get_papers(
         not_found_ids = self._get_not_found_ids(paper_ids, papers)
 
         if not_found_ids:
-            warnings.warn(f"IDs not found: {not_found_ids}")
+            logger.warning(f"IDs not found: {not_found_ids}")
 
         return papers if not return_not_found else (papers, not_found_ids)
 
@@ -554,7 +566,7 @@ async def get_authors(
         not_found_ids = list(set(author_ids) - set(found_ids))
 
         if not_found_ids:
-            warnings.warn(f"IDs not found: {not_found_ids}")
+            logger.warning(f"IDs not found: {not_found_ids}")
 
         return authors if not return_not_found else (authors, not_found_ids)
 

diff --git a/semanticscholar/SemanticScholar.py b/semanticscholar/SemanticScholar.py
@@ -31,7 +31,6 @@ def __init__(
         '''
         nest_asyncio.apply()
         self._timeout = timeout
-        self._debug = debug
         self._retry = retry
         self._AsyncSemanticScholar = AsyncSemanticScholar(
             timeout=timeout,
@@ -40,6 +39,7 @@ def __init__(
             debug=debug,
             retry=retry
         )
+        self.debug = debug
 
     @property
     def timeout(self) -> int:

diff --git a/tests/data/debug_output.txt b/tests/data/debug_output.txt
@@ -1,15 +1,4 @@
---------------------------------------------------------------------------------
-Method: POST
-
-URL:
-https://api.semanticscholar.org/graph/v1/paper/batch?fields=abstract,authors,citationCount,citationStyles,corpusId,externalIds,fieldsOfStudy,influentialCitationCount,isOpenAccess,journal,openAccessPdf,paperId,publicationDate,publicationTypes,publicationVenue,referenceCount,s2FieldsOfStudy,title,url,venue,year
-
-Headers:
-{'x-api-key': 'F@k3K3y'}
-
-Payload:
-{'ids': ['CorpusId:470667', '10.2139/ssrn.2250500', '0f40b1f08821e22e859c6050916cec3667778613']}
-
-cURL command:
-curl -X POST -H 'x-api-key: F@k3K3y' -d '{"ids": ["CorpusId:470667", "10.2139/ssrn.2250500", "0f40b1f08821e22e859c6050916cec3667778613"]}' https://api.semanticscholar.org/graph/v1/paper/batch?fields=abstract,authors,citationCount,citationStyles,corpusId,externalIds,fieldsOfStudy,influentialCitationCount,isOpenAccess,journal,openAccessPdf,paperId,publicationDate,publicationTypes,publicationVenue,referenceCount,s2FieldsOfStudy,title,url,venue,year
---------------------------------------------------------------------------------
+DEBUG:semanticscholar:HTTP Request: POST https://api.semanticscholar.org/graph/v1/paper/batch?fields=abstract,authors,citationCount,citationStyles,corpusId,externalIds,fieldsOfStudy,influentialCitationCount,isOpenAccess,journal,openAccessPdf,paperId,publicationDate,publicationTypes,publicationVenue,referenceCount,s2FieldsOfStudy,title,url,venue,year
+DEBUG:semanticscholar:Headers: {'x-api-key': 'F@k3K3y'}
+DEBUG:semanticscholar:Payload: {'ids': ['CorpusId:470667', '10.2139/ssrn.2250500', '0f40b1f08821e22e859c6050916cec3667778613']}
+DEBUG:semanticscholar:cURL command: curl -X POST -H 'x-api-key: F@k3K3y' -d '{"ids": ["CorpusId:470667", "10.2139/ssrn.2250500", "0f40b1f08821e22e859c6050916cec3667778613"]}' https://api.semanticscholar.org/graph/v1/paper/batch?fields=abstract,authors,citationCount,citationStyles,corpusId,externalIds,fieldsOfStudy,influentialCitationCount,isOpenAccess,journal,openAccessPdf,paperId,publicationDate,publicationTypes,publicationVenue,referenceCount,s2FieldsOfStudy,title,url,venue,year
diff --git a/tests/test_semanticscholar.py b/tests/test_semanticscholar.py
@@ -1,29 +1,31 @@
+import asyncio
 import io
 import json
+import logging
 import sys
 import unittest
-import asyncio
 from datetime import datetime
-from httpx import TimeoutException
+
 import vcr
+from httpx import TimeoutException
 
-from semanticscholar.Author import Author
 from semanticscholar.AsyncSemanticScholar import AsyncSemanticScholar
+from semanticscholar.Author import Author
 from semanticscholar.Citation import Citation
 from semanticscholar.Journal import Journal
 from semanticscholar.Paper import Paper
 from semanticscholar.PublicationVenue import PublicationVenue
 from semanticscholar.Reference import Reference
 from semanticscholar.SemanticScholar import SemanticScholar
 from semanticscholar.SemanticScholarException import (
-    BadQueryParametersException, ObjectNotFoundException, NoMorePagesException)
+    BadQueryParametersException, NoMorePagesException, ObjectNotFoundException)
 from semanticscholar.Tldr import Tldr
 
 test_vcr = vcr.VCR(
     cassette_library_dir='tests/data',
     path_transformer=vcr.VCR.ensure_suffix('.yaml'),
     record_mode=['new_episodes'],
-    match_on=['uri', 'method', 'body'],
+    match_on=['uri', 'method', 'raw_body'],
     drop_unused_requests=True
 )
 
@@ -196,8 +198,9 @@ def test_get_papers_not_found_warning(self):
             'CorpusId:470667',
             '10.2139/ssrn.2250500',
             '0f40b1f08821e22e859c6050916cec3667778613']
-        with self.assertWarns(UserWarning):
+        with self.assertLogs(level='WARNING') as log:
             self.sch.get_papers(list_of_paper_ids)
+            self.assertIn('IDs not found: [\'CorpusId:211530585\']', log.output[0])
 
     @test_vcr.use_cassette
     def test_get_papers_return_not_found(self):
@@ -275,8 +278,9 @@ def test_get_authors_list_empty(self):
     @test_vcr.use_cassette
     def test_get_authors_not_found_warning(self):
         list_of_author_ids = ['0', '3234559', '1726629', '1711844']
-        with self.assertWarns(UserWarning):
+        with self.assertLogs(level='WARNING') as log:
             self.sch.get_authors(list_of_author_ids)
+            self.assertIn('IDs not found: [\'0\']', log.output[0])
 
     @test_vcr.use_cassette
     def test_get_authors_return_not_found(self):
@@ -563,21 +567,18 @@ def test_empty_paginated_results(self):
 
     @test_vcr.use_cassette
     def test_debug(self):
+        logging.basicConfig(level=logging.DEBUG)
         with open('tests/data/debug_output.txt', 'r') as file:
             expected_output = file.read()
-        captured_stdout = io.StringIO()
-        sys.stdout = captured_stdout
-        self.sch = SemanticScholar(debug=True, api_key='F@k3K3y')
-        self.assertEqual(self.sch.debug, True)
+        self.sch = SemanticScholar(api_key='F@k3K3y')
         list_of_paper_ids = [
             'CorpusId:470667',
             '10.2139/ssrn.2250500',
             '0f40b1f08821e22e859c6050916cec3667778613']
-        with self.assertRaises(PermissionError):
+        with self.assertLogs(level='DEBUG') as log, \
+                self.assertRaises(PermissionError):
             self.sch.get_papers(list_of_paper_ids)
-        sys.stdout = sys.__stdout__
-        self.assertEqual(captured_stdout.getvalue().strip(),
-                         expected_output.strip())
+            self.assertIn(expected_output, log.output)
 
 class AsyncSemanticScholarTest(unittest.IsolatedAsyncioTestCase):
 
@@ -621,8 +622,9 @@ async def test_get_papers_not_found_warning_async(self):
             'CorpusId:470667',
             '10.2139/ssrn.2250500',
             '0f40b1f08821e22e859c6050916cec3667778613']
-        with self.assertWarns(UserWarning):
+        with self.assertLogs(level='WARNING') as log:
             await self.sch.get_papers(list_of_paper_ids)
+            self.assertIn('IDs not found: [\'CorpusId:211530585\']', log.output[0])
 
     @test_vcr.use_cassette
     async def test_get_papers_return_not_found_async(self):
@@ -689,8 +691,9 @@ async def test_get_authors_list_empty_async(self):
     @test_vcr.use_cassette
     async def test_get_authors_not_found_warning_async(self):
         list_of_author_ids = ['0', '3234559', '1726629', '1711844']
-        with self.assertWarns(UserWarning):
+        with self.assertLogs(level='WARNING') as log:
             await self.sch.get_authors(list_of_author_ids)
+            self.assertIn('IDs not found: [\'0\']', log.output[0])
 
     @test_vcr.use_cassette
     async def test_get_authors_return_not_found_async(self):