Changed regex to accept all numbers ([0-9] -> [0-9]+)

app.py

@@ -264,15 +264,15 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict[str, str]:
     chapters = []
     for line in toc_brut:
         x = line.split("\t")
-        if re.fullmatch(r"^\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d.\d.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+.\d+.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
 
     real_toc_indexes = {}
@@ -282,7 +282,15 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict[str, str]:
             x = text.index(chapter)
             real_toc_indexes[chapter] = x
         except ValueError as e:
-            real_toc_indexes[chapter] = -float("inf")
+            try:
+                number = chapter.split("\t")[0] + "\t"
+                for line in text[forewords[1]:]:
+                    if number in line:
+                        x = text.index(line)
+                        real_toc_indexes[line] = x
+                        break
+            except:
+                real_toc_indexes[chapter] = -float("inf")
 
     document = {}
     toc = list(real_toc_indexes.keys())
@@ -315,15 +323,15 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict:
     chapters = []
     for line in toc_brut:
         x = line.split("\t")
-        if re.fullmatch(r"^\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
-        if re.fullmatch(r"^\d\.\d\.\d.\d.\d\t[A-Z][a-zA-Z0-9\s,;!?'.-]*$", line):
+        if re.search(r"^\d+\.\d+\.\d+.\d+.\d+\t[\ \S]+", line):
             chapters.append(x[0] if len(x) == 1 else "\t".join(x[:2]))
 
     real_toc_indexes = {}
@@ -333,6 +341,14 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict:
             x = text.index(chapter)
             real_toc_indexes[chapter] = x
         except ValueError as e:
-            real_toc_indexes[chapter] = -float("inf")
+            try:
+                number = chapter.split("\t")[0] + "\t"
+                for line in text[forewords[1]:]:
+                    if number in line:
+                        x = text.index(line)
+                        real_toc_indexes[line] = x
+                        break
+            except:
+                real_toc_indexes[chapter] = -float("inf")
 
     return create_nested_structure(chapters, text, real_toc_indexes)