Update regex
Browse files
app.py
CHANGED
@@ -34,6 +34,8 @@ app.add_middleware(
|
|
34 |
allow_headers=["*"],
|
35 |
)
|
36 |
|
|
|
|
|
37 |
def get_text(specification: str, version: str):
|
38 |
"""Récupère les bytes du PDF à partir d'une spécification et d'une version."""
|
39 |
doc_id = specification
|
@@ -264,7 +266,7 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict[str, str]:
|
|
264 |
chapters = []
|
265 |
for line in toc_brut:
|
266 |
x = line.split("\t")
|
267 |
-
m = re.search(
|
268 |
if m and any(line in c for c in text[forewords[0]:forewords[1]]):
|
269 |
chapters.append(line)
|
270 |
print(line)
|
@@ -306,7 +308,7 @@ def get_file_from_spec_id_version(req: SpecRequest) -> Dict:
|
|
306 |
chapters = []
|
307 |
for line in toc_brut:
|
308 |
x = line.split("\t")
|
309 |
-
m = re.search(
|
310 |
if m and any(line in c for c in text[forewords[0]:forewords[1]]):
|
311 |
chapters.append(line)
|
312 |
print(line)
|
|
|
34 |
allow_headers=["*"],
|
35 |
)
|
36 |
|
37 |
+
regex = r"^(\d+[a-z]?(?:\.\d+)*)\t[\ \S]+$"
|
38 |
+
|
39 |
def get_text(specification: str, version: str):
|
40 |
"""Récupère les bytes du PDF à partir d'une spécification et d'une version."""
|
41 |
doc_id = specification
|
|
|
266 |
chapters = []
|
267 |
for line in toc_brut:
|
268 |
x = line.split("\t")
|
269 |
+
m = re.search(regex, line)
|
270 |
if m and any(line in c for c in text[forewords[0]:forewords[1]]):
|
271 |
chapters.append(line)
|
272 |
print(line)
|
|
|
308 |
chapters = []
|
309 |
for line in toc_brut:
|
310 |
x = line.split("\t")
|
311 |
+
m = re.search(regex, line)
|
312 |
if m and any(line in c for c in text[forewords[0]:forewords[1]]):
|
313 |
chapters.append(line)
|
314 |
print(line)
|