scitex 2.5.0__py3-none-any.whl → 2.7.0__py3-none-any.whl

scitex/scholar/core/journal_normalizer.py

@@ -98,7 +98,7 @@ class JournalNormalizer:
     Data is cached locally with daily refresh from OpenAlex.
     """
 
-    _instance: Optional['JournalNormalizer'] = None
+    _instance: Optional["JournalNormalizer"] = None
 
     def __init__(self, cache_dir: Optional[Path] = None):
         self._cache_dir = cache_dir or _get_default_cache_dir()
@@ -118,7 +118,7 @@ class JournalNormalizer:
         self._journal_count = 0
 
     @classmethod
-    def get_instance(cls, cache_dir: Optional[Path] = None) -> 'JournalNormalizer':
+    def get_instance(cls, cache_dir: Optional[Path] = None) -> "JournalNormalizer":
         """Get singleton instance."""
         if cls._instance is None:
             cls._instance = cls(cache_dir)
@@ -129,9 +129,9 @@ class JournalNormalizer:
         if not self._cache_file.exists():
             return False
         try:
-            with open(self._cache_file, 'r') as f:
+            with open(self._cache_file, "r") as f:
                 data = json.load(f)
-            cached_time = data.get('timestamp', 0)
+            cached_time = data.get("timestamp", 0)
             return (time.time() - cached_time) < CACHE_TTL_SECONDS
         except (json.JSONDecodeError, IOError):
             return False
@@ -141,14 +141,14 @@ class JournalNormalizer:
         if not self._cache_file.exists():
             return False
         try:
-            with open(self._cache_file, 'r') as f:
+            with open(self._cache_file, "r") as f:
                 data = json.load(f)
 
-            self._issn_l_data = data.get('issn_l_data', {})
-            self._name_to_issn_l = data.get('name_to_issn_l', {})
-            self._issn_to_issn_l = data.get('issn_to_issn_l', {})
-            self._abbrev_to_issn_l = data.get('abbrev_to_issn_l', {})
-            self._last_updated = data.get('timestamp', 0)
+            self._issn_l_data = data.get("issn_l_data", {})
+            self._name_to_issn_l = data.get("name_to_issn_l", {})
+            self._issn_to_issn_l = data.get("issn_to_issn_l", {})
+            self._abbrev_to_issn_l = data.get("abbrev_to_issn_l", {})
+            self._last_updated = data.get("timestamp", 0)
             self._journal_count = len(self._issn_l_data)
             self._loaded = True
 
@@ -163,14 +163,14 @@ class JournalNormalizer:
         try:
             self._cache_dir.mkdir(parents=True, exist_ok=True)
             data = {
-                'timestamp': time.time(),
-                'journal_count': len(self._issn_l_data),
-                'issn_l_data': self._issn_l_data,
-                'name_to_issn_l': self._name_to_issn_l,
-                'issn_to_issn_l': self._issn_to_issn_l,
-                'abbrev_to_issn_l': self._abbrev_to_issn_l,
+                "timestamp": time.time(),
+                "journal_count": len(self._issn_l_data),
+                "issn_l_data": self._issn_l_data,
+                "name_to_issn_l": self._name_to_issn_l,
+                "issn_to_issn_l": self._issn_to_issn_l,
+                "abbrev_to_issn_l": self._abbrev_to_issn_l,
             }
-            with open(self._cache_file, 'w') as f:
+            with open(self._cache_file, "w") as f:
                 json.dump(data, f)
             logger.info(f"Saved {len(self._issn_l_data)} journals to normalizer cache")
         except IOError as e:
@@ -183,25 +183,25 @@ class JournalNormalizer:
         Args:
             source_data: OpenAlex source object with display_name, issn_l, etc.
         """
-        issn_l = source_data.get('issn_l')
+        issn_l = source_data.get("issn_l")
         if not issn_l:
             return
 
         issn_l = _normalize_issn(issn_l)
-        display_name = source_data.get('display_name', '')
-        abbreviated_title = source_data.get('abbreviated_title', '')
-        alternate_titles = source_data.get('alternate_titles', []) or []
-        issns = source_data.get('issn', []) or []
-        is_oa = source_data.get('is_oa', False)
+        display_name = source_data.get("display_name", "")
+        abbreviated_title = source_data.get("abbreviated_title", "")
+        alternate_titles = source_data.get("alternate_titles", []) or []
+        issns = source_data.get("issn", []) or []
+        is_oa = source_data.get("is_oa", False)
 
         # Store full metadata
         self._issn_l_data[issn_l] = {
-            'canonical_name': display_name,
-            'abbreviated_title': abbreviated_title,
-            'alternate_titles': alternate_titles,
-            'issns': [_normalize_issn(i) for i in issns if i],
-            'is_oa': is_oa,
-            'publisher': source_data.get('host_organization_name', ''),
+            "canonical_name": display_name,
+            "abbreviated_title": abbreviated_title,
+            "alternate_titles": alternate_titles,
+            "issns": [_normalize_issn(i) for i in issns if i],
+            "is_oa": is_oa,
+            "publisher": source_data.get("host_organization_name", ""),
         }
 
         # Build lookup indexes
@@ -231,7 +231,9 @@ class JournalNormalizer:
                 self._issn_to_issn_l[norm_issn] = issn_l
         self._issn_to_issn_l[issn_l] = issn_l  # Self-reference
 
-    async def _fetch_journals_async(self, max_pages: int = 500, filter_oa_only: bool = False) -> None:
+    async def _fetch_journals_async(
+        self, max_pages: int = 500, filter_oa_only: bool = False
+    ) -> None:
         """
         Fetch journal data from OpenAlex API.
 
@@ -260,13 +262,15 @@ class JournalNormalizer:
                 )
 
                 try:
-                    async with session.get(url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+                    async with session.get(
+                        url, timeout=aiohttp.ClientTimeout(total=30)
+                    ) as resp:
                         if resp.status != 200:
                             logger.warning(f"OpenAlex API returned {resp.status}")
                             break
 
                         data = await resp.json()
-                        results = data.get('results', [])
+                        results = data.get("results", [])
 
                         if not results:
                             break
@@ -275,8 +279,8 @@ class JournalNormalizer:
                             self._add_journal(source)
 
                         # Get next cursor
-                        meta = data.get('meta', {})
-                        next_cursor = meta.get('next_cursor')
+                        meta = data.get("meta", {})
+                        next_cursor = meta.get("next_cursor")
                         if not next_cursor or next_cursor == cursor:
                             break
                         cursor = next_cursor
@@ -284,7 +288,9 @@ class JournalNormalizer:
 
                         # Progress log
                         if pages_fetched % 20 == 0:
-                            logger.info(f"Fetched {pages_fetched} pages, {len(self._issn_l_data)} journals...")
+                            logger.info(
+                                f"Fetched {pages_fetched} pages, {len(self._issn_l_data)} journals..."
+                            )
 
                 except asyncio.TimeoutError:
                     logger.warning("OpenAlex API timeout")
@@ -301,7 +307,9 @@ class JournalNormalizer:
             self._save_to_cache()
             logger.info(f"Fetched {self._journal_count} journals from OpenAlex")
 
-    def _fetch_journals_sync(self, max_pages: int = 500, filter_oa_only: bool = False) -> None:
+    def _fetch_journals_sync(
+        self, max_pages: int = 500, filter_oa_only: bool = False
+    ) -> None:
         """Synchronous wrapper for fetching journals."""
         try:
             loop = asyncio.get_event_loop()
@@ -348,7 +356,7 @@ class JournalNormalizer:
             return None
 
         # Check if it's an ISSN
-        if re.match(r'^\d{4}-?\d{3}[\dXx]$', journal_name.replace(" ", "")):
+        if re.match(r"^\d{4}-?\d{3}[\dXx]$", journal_name.replace(" ", "")):
             norm_issn = _normalize_issn(journal_name)
             if norm_issn in self._issn_to_issn_l:
                 return self._issn_to_issn_l[norm_issn]
@@ -378,7 +386,7 @@ class JournalNormalizer:
         """
         issn_l = self.get_issn_l(journal_name)
         if issn_l and issn_l in self._issn_l_data:
-            return self._issn_l_data[issn_l].get('canonical_name', journal_name)
+            return self._issn_l_data[issn_l].get("canonical_name", journal_name)
         return journal_name
 
     def get_abbreviation(self, journal_name: str) -> Optional[str]:
@@ -393,7 +401,7 @@ class JournalNormalizer:
         """
         issn_l = self.get_issn_l(journal_name)
         if issn_l and issn_l in self._issn_l_data:
-            return self._issn_l_data[issn_l].get('abbreviated_title')
+            return self._issn_l_data[issn_l].get("abbreviated_title")
         return None
 
     def get_journal_info(self, journal_name: str) -> Optional[Dict[str, Any]]:
@@ -408,10 +416,7 @@ class JournalNormalizer:
         """
         issn_l = self.get_issn_l(journal_name)
         if issn_l and issn_l in self._issn_l_data:
-            return {
-                'issn_l': issn_l,
-                **self._issn_l_data[issn_l]
-            }
+            return {"issn_l": issn_l, **self._issn_l_data[issn_l]}
         return None
 
     def is_same_journal(self, name1: str, name2: str) -> bool:
@@ -446,7 +451,7 @@ class JournalNormalizer:
         """
         issn_l = self.get_issn_l(journal_name)
         if issn_l and issn_l in self._issn_l_data:
-            return self._issn_l_data[issn_l].get('is_oa', False)
+            return self._issn_l_data[issn_l].get("is_oa", False)
         return False
 
     def search(self, query: str, limit: int = 10) -> List[Dict[str, Any]]:
@@ -471,10 +476,7 @@ class JournalNormalizer:
         for norm_name, issn_l in self._name_to_issn_l.items():
             if norm_query in norm_name:
                 if issn_l in self._issn_l_data:
-                    results.append({
-                        'issn_l': issn_l,
-                        **self._issn_l_data[issn_l]
-                    })
+                    results.append({"issn_l": issn_l, **self._issn_l_data[issn_l]})
                     if len(results) >= limit:
                         break
 
@@ -490,12 +492,13 @@ class JournalNormalizer:
     def cache_age_hours(self) -> float:
         """Get cache age in hours."""
         if self._last_updated == 0:
-            return float('inf')
+            return float("inf")
         return (time.time() - self._last_updated) / 3600
 
 
 # ==================== Convenience Functions ====================
 
+
 def get_journal_normalizer(cache_dir: Optional[Path] = None) -> JournalNormalizer:
     """Get the journal normalizer singleton."""
     return JournalNormalizer.get_instance(cache_dir)

scitex/scholar/core/oa_cache.py

@@ -48,8 +48,8 @@ class OASourcesCache:
     - Handles abbreviations, variants, and historical names
     """
 
-    _instance: Optional['OASourcesCache'] = None
-    _lock = asyncio.Lock() if hasattr(asyncio, 'Lock') else None
+    _instance: Optional["OASourcesCache"] = None
+    _lock = asyncio.Lock() if hasattr(asyncio, "Lock") else None
 
     def __init__(self, cache_dir: Optional[Path] = None):
         self._cache_dir = cache_dir or _get_default_cache_dir()
@@ -64,7 +64,7 @@ class OASourcesCache:
         self._loaded = False
 
     @classmethod
-    def get_instance(cls, cache_dir: Optional[Path] = None) -> 'OASourcesCache':
+    def get_instance(cls, cache_dir: Optional[Path] = None) -> "OASourcesCache":
         """Get singleton instance."""
         if cls._instance is None:
             cls._instance = cls(cache_dir)
@@ -75,9 +75,9 @@ class OASourcesCache:
         if not self._cache_file.exists():
             return False
         try:
-            with open(self._cache_file, 'r') as f:
+            with open(self._cache_file, "r") as f:
                 data = json.load(f)
-            cached_time = data.get('timestamp', 0)
+            cached_time = data.get("timestamp", 0)
             return (time.time() - cached_time) < CACHE_TTL_SECONDS
         except (json.JSONDecodeError, IOError):
             return False
@@ -87,12 +87,12 @@ class OASourcesCache:
         if not self._cache_file.exists():
             return False
         try:
-            with open(self._cache_file, 'r') as f:
+            with open(self._cache_file, "r") as f:
                 data = json.load(f)
 
-            self._oa_source_names = set(data.get('source_names', []))
-            self._oa_issns = set(data.get('issns', []))
-            self._last_updated = data.get('timestamp', 0)
+            self._oa_source_names = set(data.get("source_names", []))
+            self._oa_issns = set(data.get("issns", []))
+            self._last_updated = data.get("timestamp", 0)
             self._loaded = True
 
             logger.info(f"Loaded {len(self._oa_source_names)} OA sources from cache")
@@ -106,12 +106,12 @@ class OASourcesCache:
         try:
             self._cache_dir.mkdir(parents=True, exist_ok=True)
             data = {
-                'timestamp': time.time(),
-                'source_names': list(self._oa_source_names),
-                'issns': list(self._oa_issns),
-                'count': len(self._oa_source_names),
+                "timestamp": time.time(),
+                "source_names": list(self._oa_source_names),
+                "issns": list(self._oa_issns),
+                "count": len(self._oa_source_names),
             }
-            with open(self._cache_file, 'w') as f:
+            with open(self._cache_file, "w") as f:
                 json.dump(data, f)
             logger.info(f"Saved {len(self._oa_source_names)} OA sources to cache")
         except IOError as e:
@@ -143,31 +143,33 @@ class OASourcesCache:
                 )
 
                 try:
-                    async with session.get(url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+                    async with session.get(
+                        url, timeout=aiohttp.ClientTimeout(total=30)
+                    ) as resp:
                         if resp.status != 200:
                             logger.warning(f"OpenAlex API returned {resp.status}")
                             break
 
                         data = await resp.json()
-                        results = data.get('results', [])
+                        results = data.get("results", [])
 
                         if not results:
                             break
 
                         for source in results:
-                            name = source.get('display_name', '')
+                            name = source.get("display_name", "")
                             if name:
                                 source_names.add(name.lower())
 
                             # Also store ISSNs for precise matching
-                            source_issns = source.get('issn', []) or []
+                            source_issns = source.get("issn", []) or []
                             for issn in source_issns:
                                 if issn:
                                     issns.add(issn)
 
                         # Get next cursor
-                        meta = data.get('meta', {})
-                        next_cursor = meta.get('next_cursor')
+                        meta = data.get("meta", {})
+                        next_cursor = meta.get("next_cursor")
                         if not next_cursor or next_cursor == cursor:
                             break
                         cursor = next_cursor
@@ -175,7 +177,9 @@ class OASourcesCache:
 
                         # Progress log every 10 pages
                         if pages_fetched % 10 == 0:
-                            logger.info(f"Fetched {pages_fetched} pages, {len(source_names)} sources so far...")
+                            logger.info(
+                                f"Fetched {pages_fetched} pages, {len(source_names)} sources so far..."
+                            )
 
                 except asyncio.TimeoutError:
                     logger.warning("OpenAlex API timeout")
@@ -249,7 +253,7 @@ class OASourcesCache:
         if not issn:
             return False
         # Normalize ISSN format
-        issn = issn.replace('-', '').upper()
+        issn = issn.replace("-", "").upper()
         return issn in self._oa_issns or f"{issn[:4]}-{issn[4:]}" in self._oa_issns
 
     @property
@@ -262,7 +266,7 @@ class OASourcesCache:
     def cache_age_hours(self) -> float:
         """Get cache age in hours."""
         if self._last_updated == 0:
-            return float('inf')
+            return float("inf")
         return (time.time() - self._last_updated) / 3600
 
 

scitex/scholar/core/open_access.py

@@ -28,6 +28,7 @@ logger = logging.getLogger(__name__)
 # Load OA config from default.yaml (single source of truth)
 _config = None
 
+
 def _get_config() -> ScholarConfig:
     """Get or create singleton config instance."""
     global _config
@@ -58,17 +59,19 @@ def _get_unpaywall_email() -> str:
 
 class OAStatus(Enum):
     """Open Access status categories (aligned with Unpaywall)."""
-    GOLD = "gold"        # Published in OA journal (DOAJ listed)
-    GREEN = "green"      # Available in repository (arXiv, PMC, etc.)
-    HYBRID = "hybrid"    # OA article in subscription journal
-    BRONZE = "bronze"    # Free to read on publisher site, but no license
-    CLOSED = "closed"    # Paywalled
+
+    GOLD = "gold"  # Published in OA journal (DOAJ listed)
+    GREEN = "green"  # Available in repository (arXiv, PMC, etc.)
+    HYBRID = "hybrid"  # OA article in subscription journal
+    BRONZE = "bronze"  # Free to read on publisher site, but no license
+    CLOSED = "closed"  # Paywalled
     UNKNOWN = "unknown"  # Status not determined
 
 
 @dataclass
 class OAResult:
     """Result of open access detection."""
+
     is_open_access: bool
     status: OAStatus
     oa_url: Optional[str] = None
@@ -84,7 +87,7 @@ class OAResult:
 # arXiv ID patterns
 ARXIV_PATTERNS = [
     re.compile(r"^\d{4}\.\d{4,5}(v\d+)?$"),  # New format: 2301.12345
-    re.compile(r"^[a-z-]+/\d{7}(v\d+)?$"),   # Old format: hep-th/9901001
+    re.compile(r"^[a-z-]+/\d{7}(v\d+)?$"),  # Old format: hep-th/9901001
     re.compile(r"^arxiv:\d{4}\.\d{4,5}(v\d+)?$", re.IGNORECASE),
 ]
 
@@ -135,6 +138,7 @@ def is_open_access_journal(journal_name: str, use_cache: bool = True) -> bool:
     if use_cache:
         try:
             from .oa_cache import is_oa_journal_cached
+
             if is_oa_journal_cached(journal_name):
                 return True
         except ImportError:
@@ -144,6 +148,7 @@ def is_open_access_journal(journal_name: str, use_cache: bool = True) -> bool:
     if use_cache:
         try:
             from .journal_normalizer import get_journal_normalizer
+
             normalizer = get_journal_normalizer()
             if normalizer.is_open_access(journal_name):
                 return True
@@ -212,7 +217,9 @@ def detect_oa_from_identifiers(
     if source and is_open_access_source(source):
         return OAResult(
             is_open_access=True,
-            status=OAStatus.GREEN if source.lower() in ["arxiv", "pmc", "biorxiv", "medrxiv"] else OAStatus.GOLD,
+            status=OAStatus.GREEN
+            if source.lower() in ["arxiv", "pmc", "biorxiv", "medrxiv"]
+            else OAStatus.GOLD,
             source=f"source_{source}",
             confidence=0.95,
         )
@@ -285,7 +292,9 @@ async def check_oa_status_unpaywall(
 
     try:
         async with aiohttp.ClientSession() as session:
-            async with session.get(url, timeout=aiohttp.ClientTimeout(total=timeout)) as resp:
+            async with session.get(
+                url, timeout=aiohttp.ClientTimeout(total=timeout)
+            ) as resp:
                 if resp.status == 404:
                     return OAResult(
                         is_open_access=False,

scitex/scholar/docs/template.py

@@ -5,9 +5,8 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
-__FILE__ = (
-    "./src/scitex/scholar/storage/template.py"
-)
+
+__FILE__ = "./src/scitex/scholar/storage/template.py"
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
 
@@ -55,6 +54,8 @@ logger = logging.getLogger(__name__)
 # CONFIG = stx.io.load_configs()
 
 """Functions & Classes"""
+
+
 def main(args):
     return 0
 

scitex/scholar/examples/00_config.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -45,6 +46,8 @@ import scitex as stx
 """Parameters"""
 
 """Functions & Classes"""
+
+
 def demonstrate_basic_paths(config) -> None:
     """Show basic directory paths and creation.
 
@@ -79,15 +82,13 @@ def demonstrate_library_system(config) -> None:
     print(f"Project library: {config.get_library_project_dir('my_project')}")
     print(f"Master storage: {config.get_library_master_dir()}")
 
-    storage_path, readable_name, paper_id = (
-        config.paths.get_paper_storage_paths(
-            doi="10.1038/nature12373",
-            title="Attention Is All You Need",
-            authors=["Vaswani, Ashish", "Shazeer, Noam"],
-            journal="Nature",
-            year=2017,
-            project="transformer_papers",
-        )
+    storage_path, readable_name, paper_id = config.paths.get_paper_storage_paths(
+        doi="10.1038/nature12373",
+        title="Attention Is All You Need",
+        authors=["Vaswani, Ashish", "Shazeer, Noam"],
+        journal="Nature",
+        year=2017,
+        project="transformer_papers",
     )
 
     print(f"Paper storage example:")

scitex/scholar/examples/01_auth.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -41,6 +42,8 @@ import scitex as stx
 """Parameters"""
 
 """Functions & Classes"""
+
+
 async def setup_authentication() -> bool:
     """Set up and validate ScholarAuthManager authentication.
 

scitex/scholar/examples/02_browser.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -41,9 +42,11 @@ import scitex as stx
 """Parameters"""
 
 """Functions & Classes"""
+
+
 async def demonstrate_browser_usage() -> bool:
     """Demonstrate browser manager with authentication.
-    
+
     Returns
     -------
     bool
@@ -51,27 +54,28 @@ async def demonstrate_browser_usage() -> bool:
     """
     from scitex.scholar.auth import ScholarAuthManager
     from scitex.scholar.browser import ScholarBrowserManager
-    
+
     print("🌐 Initializing browser with authentication...")
-    
+
     browser_manager = ScholarBrowserManager(
         chrome_profile_name="system",
         browser_mode="interactive",
         auth_manager=ScholarAuthManager(),
     )
 
-    browser, context = (
-        await browser_manager.get_authenticated_browser_and_context_async()
-    )
+    (
+        browser,
+        context,
+    ) = await browser_manager.get_authenticated_browser_and_context_async()
 
     page = await context.new_page()
-    
+
     print("📖 Navigating to scitex.ai...")
     await page.goto("https://scitex.ai")
-    
+
     print("⏳ Waiting 10 seconds for demonstration...")
     await asyncio.sleep(10)
-    
+
     print("✅ Browser demonstration completed")
     return True
 
@@ -93,7 +97,7 @@ async def main_async(args) -> bool:
     print("=" * 40)
 
     success = await demonstrate_browser_usage()
-    
+
     if success:
         print("✅ Browser workflow completed successfully")
     else:

scitex/scholar/examples/03_01-engine.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -44,6 +45,8 @@ import scitex as stx
 """Parameters"""
 
 """Functions & Classes"""
+
+
 async def search_by_queries(
     title: str = None, doi: str = None, use_cache: bool = False
 ) -> dict:

scitex/scholar/examples/03_02-engine-for-bibtex.py

@@ -5,6 +5,7 @@
 # ----------------------------------------
 from __future__ import annotations
 import os
+
 __FILE__ = __file__
 __DIR__ = os.path.dirname(__FILE__)
 # ----------------------------------------
@@ -46,6 +47,8 @@ import scitex as stx
 """Parameters"""
 
 """Functions & Classes"""
+
+
 async def search_bibtex_metadata(
     bibtex_path: str, use_cache: bool = True, n_samples: int = None
 ) -> list:
@@ -88,9 +91,7 @@ async def main_async(args):
 
     pprint(batched_metadata)
 
-    output_name = selected_path.split("/")[-1].replace(
-        ".bib", "_metadata.json"
-    )
+    output_name = selected_path.split("/")[-1].replace(".bib", "_metadata.json")
     output_path = f"./data/scholar/{output_name}"
 
     stx.io.save(batched_metadata, output_path, symlink_from_cwd=True)