Parse QCU correct answers with Xpath and Regex

tetras_extraction/macao_12/script/extract_page.py

@@ -50,14 +50,12 @@ class RegexParser:
             raise ParseError("Failed to find function 'entrerDonnees'")
         body = func_split[1]
 
-        activity_type, activity_var_name = self.parse_activity_constructor(body)
-        print(activity_type, file=output)
+        activity_type, activity_var_name = self._parse_activity_constructor(body)
+        print(activity_type, end="", file=output)
+        if activity_type == "ExerciceQC_QCU":
+            print(" ", self._parse_qcu_answers(body), end="", file=output)
 
-        for line in body.splitlines():
-            line = line.strip()
-            pass
-
-    def parse_activity_constructor(self, code: str) -> tuple[str, str]:
+    def _parse_activity_constructor(self, code: str) -> tuple[str, str]:
         """
         Find activity constructor call, return the activity type
         and resulting variable name.
@@ -80,6 +78,24 @@ class RegexParser:
             act_type += "_" + args.replace('"', "")
         return act_type, var_name
 
+    def _parse_qcu_answers(self, code: str) -> list[bool]:
+        """Parse the correct answers for a QCU activity, as a list of booleans"""
+        correct_choices = []
+        index = 0
+        for line in code.splitlines():
+            line = line.strip()
+            m = re.match(r"var nr = (\d+);", line)
+            if m is not None:
+                # "index" line
+                index = int(m.group(1))
+            elif line == "exo.tabStylesR[nr] = CODE_F;":
+                # "incorrect answer" line
+                insert_grow(correct_choices, index, False, fill_value=False)
+            elif line == "exo.tabStylesR[nr] = CODE_V;":
+                # "correct answer" line
+                insert_grow(correct_choices, index, True, fill_value=False)
+        return correct_choices
+
     def __str__(self) -> str:
         return "RegexParser"
 
@@ -108,8 +124,10 @@ class XpathParser:
         xml = self.to_xml(jstree.toDict(), "jstree")
         try:
             self.fun = self.request_function(xml)[0]
-            print(self._parse_activity_type(), file=output)
-            # self._parse_qcu_choices()
+            act_type = self._parse_activity_type()
+            print(act_type, end="", file=output)
+            if act_type == "ExerciceQC_QCU":
+                print(" ", self._parse_qcu_answers(), end="", file=output)
         except Exception as e:
             raise ParseError(e)
 
@@ -124,18 +142,20 @@ class XpathParser:
             case other:
                 return other
 
-    def _parse_qcu_choices(self):
+    def _parse_qcu_answers(self) -> list[bool]:
+        """Parse the correct answers for a QCU activity, as a list of booleans"""
         indexes_and_values = self.request_index_and_values(self.fun)
         correct_choices = []
+        index = 0
         for e in indexes_and_values:
             value = e.xpath("@value")
             if len(value) != 0:
                 # "index line"
-                index = value[0]
+                index = int(value[0])
             else:
                 # "true line"
                 insert_grow(correct_choices, index, True, fill_value=False)
-        print(correct_choices)
+        return correct_choices
 
     def to_xml(self, obj, tag_name: Optional[str] = None):
         """Recursively convert an object structure to an XML `ElementTree`.
@@ -242,7 +262,7 @@ class MatchParser:
                 pass
 
     def print(self, s: str):
-        print(s, file=self.output)
+        print(s, end="", file=self.output)
 
     def match_function(self, func: dict):
         """Checks if `func` matches a function declaration named `entrerDonnees`,
@@ -301,7 +321,7 @@ def parse_page(graph: Graph, filepath: str, id: str):
     # Try different parsers, each writing to a different file to compare their results
     for parser in [XpathParser(), MatchParser(graph, id), RegexParser()]:
         with open(f"/tmp/{str(parser)}.txt", "a") as f:
-            print(f"{id:8}", end="", file=f)
+            print(f"\n{id:8}", end="", file=f)
             try:
                 parser.parse(js, output=f)
             except ParseError as e: