From 2e420c0d4b72f6a914e124565c7ca649d0b93764 Mon Sep 17 00:00:00 2001
From: David Huggins-Daines <dhd@ecolingui.ca>
Date: Tue, 30 Jul 2024 15:59:30 -0400
Subject: [PATCH] fix: verifier presence de zonage

---
 alexi/analyse.py | 10 ++++++----
 alexi/extract.py |  4 +++-
 alexi/link.py    |  2 +-
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/alexi/analyse.py b/alexi/analyse.py
index c5dd99d..15ab897 100644
--- a/alexi/analyse.py
+++ b/alexi/analyse.py
@@ -9,7 +9,7 @@
 from collections import deque
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Iterable, Iterator, NamedTuple, Optional
+from typing import Iterable, Iterator, NamedTuple, Optional, Union
 
 from pdfplumber.utils.geometry import T_bbox, calculate_area, merge_bboxes
 
@@ -481,7 +481,7 @@ def __call__(
         return doc
 
 
-def extract_zonage(doc: Document) -> dict[str, dict[str, dict[str, str]]]:
+def extract_zonage(doc: Document) -> Union[dict[str, dict[str, dict[str, str]]], None]:
     """
     Extraire les éléments du zonage d'un règlement et générer des
     metadonnées pour l'identification des hyperliens et la
@@ -490,7 +490,7 @@ def extract_zonage(doc: Document) -> dict[str, dict[str, dict[str, str]]]:
     mz: Optional[Element] = None
     if "Chapitre" not in doc.paliers:
         LOGGER.warning("Aucun chapitre présent dans %s", doc.fileid)
-        return {}
+        return None
     for c in doc.paliers["Chapitre"]:
         if "milieux et zones" in c.titre.lower():
             LOGGER.info("Extraction de milieux et zones")
@@ -498,7 +498,7 @@ def extract_zonage(doc: Document) -> dict[str, dict[str, dict[str, str]]]:
             break
     if mz is None:
         LOGGER.info("Chapitre milieux et zones non trouvé")
-        return {}
+        return None
     top = Path(doc.fileid) / "Chapitre" / mz.numero
     metadata: dict[str, dict[str, dict[str, str]]] = {
         "categorie_milieu": {},
@@ -520,4 +520,6 @@ def extract_zonage(doc: Document) -> dict[str, dict[str, dict[str, str]]]:
                     "titre": m.group(2),
                     "url": str(subsecdir),
                 }
+    if len(metadata["categorie_milieu"]) == 0 and len(metadata["milieu"]) == 0:
+        return None
     return metadata
diff --git a/alexi/extract.py b/alexi/extract.py
index 8e049bc..2d9f39d 100644
--- a/alexi/extract.py
+++ b/alexi/extract.py
@@ -414,7 +414,9 @@ def __call__(self, path: Path) -> Union[Document, None]:
         if self.pdfdata:
             doc.pdfurl = self.pdfdata.get(pdf_path.name, {}).get("url", None)
         if "zonage" in doc.titre.lower() and "zonage" not in self.metadata:
-            self.metadata["zonage"] = extract_zonage(doc)
+            zonage = extract_zonage(doc)
+            if zonage is not None:
+                self.metadata["zonage"] = zonage
         return doc
 
     def analyse(self, iob: Iterable[T_obj], pdf_path: Path):
diff --git a/alexi/link.py b/alexi/link.py
index c822ae0..d5ced61 100644
--- a/alexi/link.py
+++ b/alexi/link.py
@@ -55,7 +55,7 @@ def __init__(self, metadata: Optional[dict] = None):
         self.metadata = {"docs": {}} if metadata is None else metadata
         self.numeros = {}
         self.titles = {}
-        self.urls = set()
+        self.urls: set[str] = set()
         for docpath, info in self.metadata["docs"].items():
             self.numeros[info["numero"]] = docpath
             self.titles[normalize_title(info["titre"])] = docpath