updating and cleaning

Author: apjanco

app/main.py

@@ -21,7 +21,8 @@
 from pathlib import Path
 
 import logging
-#from app.custom_logging import CustomizeLogger
+
+# from app.custom_logging import CustomizeLogger
 
 logger = logging.getLogger(__name__)
 config_path = Path(__file__).with_name("logging_config.json")
@@ -32,8 +33,8 @@
 app = FastAPI()
 app.mount("/static", StaticFiles(directory="./app/static"), name="static")
 
-#logger = CustomizeLogger.make_logger(config_path)
-#app.logger = logger
+# logger = CustomizeLogger.make_logger(config_path)
+# app.logger = logger
 
 app.include_router(create.router)
 
@@ -56,8 +57,9 @@
 
 
 @app.get("/")
-def root(request: Request,):
-
+def root(
+    request: Request,
+):
     return templates.TemplateResponse("login.html", {"request": request})
 
 

app/routers/corpus.py

@@ -13,87 +13,94 @@
 from functools import lru_cache
 import importlib
 from ..util.manage_corpus import make_corpus
+
 templates = Jinja2Templates(directory="app/templates")
 
 router = APIRouter(dependencies=[Depends(get_current_username)])
 
-Token = namedtuple("Token", ["text", "lemma_", "pos_", "ent_type_","is_stop"])
+Token = namedtuple("Token", ["text", "lemma_", "pos_", "ent_type_", "is_stop"])
+
 
 @router.get("/update_corpus")
 async def update_corpus(background_tasks: BackgroundTasks):
     background_tasks.add_task(make_corpus)
 
 
-
 ###########
 # Lemmata #
 ###########
 
+
 @router.get("/update_lemma")
-async def update_lemma(word:str,lemma:str):
+async def update_lemma(word: str, lemma: str):
     # load lemma file, needed because we update the file
     new_lang = Path.cwd() / "new_lang"
     lang_name = list(new_lang.iterdir())[0].name
     if len(list(new_lang.iterdir())) > 0:
         lookups_path = new_lang / lang_name / "lookups"
         for lookup in lookups_path.iterdir():
-            key = lookup.stem[lookup.stem.find('_') + 1:]
-            if 'lemma' in key:
+            key = lookup.stem[lookup.stem.find("_") + 1 :]
+            if "lemma" in key:
                 lemma_file = lookup
                 lemma_data = srsly.read_json(lookup)
 
-    # remove any accidental spaces 
+    # remove any accidental spaces
     word = word.strip()
     lemma = lemma.strip()
     lemma_data[word] = lemma
     srsly.write_json(lemma_file, lemma_data)
 
+
 ###########
 # POS #
 ###########
 
+
 @router.get("/update_pos")
-async def update_pos(word:str,pos:str):
+async def update_pos(word: str, pos: str):
     # load lemma file, needed because we update the file
     new_lang = Path.cwd() / "new_lang"
     lang_name = list(new_lang.iterdir())[0].name
     if len(list(new_lang.iterdir())) > 0:
         lookups_path = new_lang / lang_name / "lookups"
         for lookup in lookups_path.iterdir():
-            key = lookup.stem[lookup.stem.find('_') + 1:]
-            if 'pos' in key:
+            key = lookup.stem[lookup.stem.find("_") + 1 :]
+            if "pos" in key:
                 pos_file = lookup
                 pos_data = srsly.read_json(lookup)
 
-    # remove any accidental spaces 
+    # remove any accidental spaces
     word = word.strip()
     pos = pos.strip()
     pos_data[word] = pos
     srsly.write_json(pos_file, pos_data)
 
+
 ###########
 # POS #
 ###########
 
+
 @router.get("/update_features")
-async def update_features(word:str,features:str):
+async def update_features(word: str, features: str):
     # load lemma file, needed because we update the file
     new_lang = Path.cwd() / "new_lang"
     lang_name = list(new_lang.iterdir())[0].name
     if len(list(new_lang.iterdir())) > 0:
         lookups_path = new_lang / lang_name / "lookups"
         for lookup in lookups_path.iterdir():
-            key = lookup.stem[lookup.stem.find('_') + 1:]
-            if 'features' in key:
+            key = lookup.stem[lookup.stem.find("_") + 1 :]
+            if "features" in key:
                 features_file = lookup
                 features_data = srsly.read_json(lookup)
 
-    # remove any accidental spaces 
+    # remove any accidental spaces
     word = word.strip()
     features = features.strip()
     features_data[word] = features
     srsly.write_json(features_file, features_data)
 
+
 ##############
 # Stop words #
 ##############
@@ -109,40 +116,42 @@ def load_stopwords():
         return STOP_WORDS
 
 
-def is_stop(word:str, STOP_WORDS:Set):
+def is_stop(word: str, STOP_WORDS: Set):
     if word in STOP_WORDS:
         return "☑"
-    else: 
+    else:
         return "☐"
 
+
 @router.get("/add_stopword")
-def add_stopword(word:str):
+def add_stopword(word: str):
     new_lang = Path.cwd() / "new_lang"
     if len(list(new_lang.iterdir())) > 0:
         path = list(new_lang.iterdir())[0]
         path = path / "stop_words.py"
         text = path.read_text()
-        #Edit only the stopwords string, otherwise we could replace other sections of the file
+        # Edit only the stopwords string, otherwise we could replace other sections of the file
         start = text.find('"""')
         end = text.find('""".split()')
         stopwords = text[start:end]
         if not word in stopwords:
-            stopwords = stopwords + ' ' + word
+            stopwords = stopwords + " " + word
             text = text[:start] + stopwords + text[end:]
             path.write_text(text)
 
+
 @router.get("/delete_stopword")
-def delete_stopword(word:str):
+def delete_stopword(word: str):
     new_lang = Path.cwd() / "new_lang"
     if len(list(new_lang.iterdir())) > 0:
         path = list(new_lang.iterdir())[0]
         path = path / "stop_words.py"
         text = path.read_text()
-        #Edit only the stopwords string, otherwise we could replace other sections of the file
+        # Edit only the stopwords string, otherwise we could replace other sections of the file
         start = text.find('"""')
         end = text.find('""".split()')
         stopwords = text[start:end]
-        stopwords = re.sub(fr'\b{word}\b', '', stopwords)
+        stopwords = re.sub(rf"\b{word}\b", "", stopwords)
         text = text[:start] + stopwords + text[end:]
         path.write_text(text)
 
@@ -151,39 +160,44 @@ def delete_stopword(word:str):
 # Corpus Page #
 ###############
 
-#@lru_cache removing to work on 3.6, but is good
+
+# @lru_cache removing to work on 3.6, but is good
 def load_lookups():
     new_lang = Path.cwd() / "new_lang"
     if len(list(new_lang.iterdir())) > 0:
         lang_name = list(new_lang.iterdir())[0].name
         lookups_path = new_lang / lang_name / "lookups"
         for lookup in lookups_path.iterdir():
-            key = lookup.stem[lookup.stem.find('_') + 1:]
-            if 'lemma' in key:
+            key = lookup.stem[lookup.stem.find("_") + 1 :]
+            if "lemma" in key:
                 lemma_data = srsly.read_json(lookup)
-            if 'features' in key:
+            if "features" in key:
                 features_data = srsly.read_json(lookup)
-            if 'pos' in key:
+            if "pos" in key:
                 pos_data = srsly.read_json(lookup)
-        return lemma_data,features_data,pos_data
+        return lemma_data, features_data, pos_data
 
 
 @router.get("/corpus")
 async def read_items(request: Request):
-    
     new_lang = Path.cwd() / "new_lang"
     if len(list(new_lang.iterdir())) > 0:
         lang_name = list(new_lang.iterdir())[0].name
         corpus_dir = new_lang / lang_name / "corpus_json"
-        tokens_json = srsly.read_json((corpus_dir / 'tokens.json'))
-        stats = srsly.read_json((corpus_dir / 'stats.json'))
+        tokens_json = srsly.read_json((corpus_dir / "tokens.json"))
+        stats = srsly.read_json((corpus_dir / "stats.json"))
         stats = srsly.json_loads(stats)
         nlp = get_nlp()
-        writing_system = nlp.vocab.writing_system['direction']
+        writing_system = nlp.vocab.writing_system["direction"]
 
         return templates.TemplateResponse(
             "corpus.html",
-            {"request": request, "stats": stats, "tokens_json": tokens_json, "writing_system":writing_system},
+            {
+                "request": request,
+                "stats": stats,
+                "tokens_json": tokens_json,
+                "writing_system": writing_system,
+            },
         )
     else:
         return templates.TemplateResponse(

app/routers/edit_code.py

@@ -44,8 +44,9 @@ async def edit_code(
 
 
 @router.post("/edit")
-async def update_code(request: Request,):
-
+async def update_code(
+    request: Request,
+):
     data = await request.json()
     type = data["type"]
     code = data["code"]
@@ -63,17 +64,16 @@ async def update_code(request: Request,):
         "edit_code.html", {"request": request, "code": code}
     )
 
+
 @router.get("/check_logs")
 async def check_logs(
     request: Request,
-    
 ):
-    context = {} 
-    context['request']   = request
+    context = {}
+    context["request"] = request
     log_file = Path.cwd() / "error.log"
     if log_file.exists():
         context["code"] = log_file.read_text()
     else:
         raise HTTPException(status_code=404, detail="File not found")
     return templates.TemplateResponse("edit_code.html", context)
-