Small fixes

Author: JWittmeyer

extractors/numbers/ip_extraction/__init__.py

@@ -22,7 +22,6 @@ def ip_extraction(request: IpExtractionModel):
     nlp = SpacySingleton.get_nlp(request.spacyTokenizer)
     doc = nlp(text)
     regex = re.compile(r"\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b")
-    regex.findall(text)
 
     ip_addresses = []
     for match in regex.finditer(text):

extractors/numbers/isbn_extraction/__init__.py

@@ -28,5 +28,5 @@ def isbn_extraction(request: IsbnExtractionModel):
     for match in regex.finditer(text):
         start, end = match.span()
         span = doc.char_span(start, end, alignment_mode="expand")
-        isbn.append([span.start, span.end, span.text])
+        isbn.append(["isbn", span.start, span.end])
     return {"isbn": isbn}

extractors/numbers/percentage_extraction/__init__.py

@@ -22,11 +22,11 @@ def percentage_extraction(request: PercentageExtractionModel):
     text = request.text
     nlp = SpacySingleton.get_nlp(request.spacyTokenizer)
     doc = nlp(text)
-    regex = re.compile(r"(?:[\d-]{17}|[\d-]{13})")
-
+    regex = re.compile(r"(-?\d+(?:[.,]\d*)?|-?[.,]\d+)%")
+    print(text,flush=True)
     p = []
     for match in regex.finditer(text):
         start, end = match.span()
         span = doc.char_span(start, end, alignment_mode="expand")
-        p.append([span.start, span.end, span.text])
+        p.append(["percentage", span.start, span.end])
     return {"percentages": p}

extractors/numbers/percentage_extraction/code_snippet_common.md

@@ -14,12 +14,12 @@ def percentage_extraction(text: str, extraction_keyword:str) -> List[Tuple[str,
 
     regex = re.compile(r"(-?\d+(?:[.,]\d*)?|-?[.,]\d+)%")
 
-    isbn_positions = []
+    percentage_positions = []
     for match in regex.finditer(text):
         start, end = match.span()
         span = doc.char_span(start, end, alignment_mode="expand")
-        isbn_positions.append((extraction_keyword, span.start, span.end))
-    return isbn_positions
+        percentage_positions.append((extraction_keyword, span.start, span.end))
+    return percentage_positions
 
 # ↑ necessary bricks function 
 # -----------------------------------------------------------------------------------------

extractors/numbers/percentage_extraction/config.py

@@ -31,20 +31,13 @@ def get_config():
                 },
                 "LABEL": {
                     "selectionType": SelectionType.CHOICE.value,
-                    "defaultValue": "isbn",
+                    "defaultValue": "percentage",
                     "optional": "false",
                     "addInfo": [
                         BricksVariableType.LABEL.value,
                         BricksVariableType.GENERIC_STRING.value,
                     ],
                 },
-                "REGEX": {
-                    "selectionType": SelectionType.STRING.value,
-                    "defaultValue": "(-?\d+(?:[.,]\d*)?|-?[.,]\d+)%",
-                    "description": "Choose any regex here",
-                    "optional": "false",
-                    "addInfo": [BricksVariableType.REGEX.value],
-                },
             },
         },
     )

extractors/words/goodbye_extraction/__init__.py

@@ -31,6 +31,6 @@ def goodbye_extraction(request: GoodbyeExtractionModel):
     for match in regex.finditer(text):
         start, end = match.span()
         span = doc.char_span(start, end, alignment_mode="expand")
-        farewell.append(["span", span.start, span.end])
+        farewell.append(["farewellWords", span.start, span.end])
 
     return {"farewellWords": farewell}