diff --git a/tetras_extraction/macao_12/script/.vscode/extensions.json b/tetras_extraction/macao_12/script/.vscode/extensions.json
new file mode 100644
index 0000000000000000000000000000000000000000..9e75ef5179cf4e5c6a85ca0508198fe49c76f4ed
--- /dev/null
+++ b/tetras_extraction/macao_12/script/.vscode/extensions.json
@@ -0,0 +1,6 @@
+{
+ "recommendations": [
+ "detachhead.basedpyright",
+ "ms-python.black-formatter"
+ ]
+}
\ No newline at end of file
diff --git a/tetras_extraction/macao_12/script/common.py b/tetras_extraction/macao_12/script/common.py
index 83512e85181b9933c1f7660f4ede92804f320032..e9aa55a848fde8c39ba901a525540c5455a4d496 100644
--- a/tetras_extraction/macao_12/script/common.py
+++ b/tetras_extraction/macao_12/script/common.py
@@ -1,9 +1,10 @@
+from os import environ, path
from sys import stderr
-from typing import Any, Optional
-from rdflib import RDFS, Graph, Literal, URIRef
-from rdflib import Namespace
-from os import path, environ
+from typing import Any
+
from lxml import html
+from rdflib import Graph, Literal, RDFS, URIRef
+from rdflib import Namespace
def env_path_or_rel_default(env_var: str, default: str) -> str:
@@ -36,19 +37,17 @@ NS = Namespace("http://www.semanticweb.org/eliott/ontologies/2024/4/macao/")
# Utility functions ############################################################
-def eprint(*args, **kwargs):
+def eprint(*args, **kwargs): # pyright: ignore[reportMissingParameterType]
"""Just like `print()`, but to standard error instead of standard output"""
print(*args, file=stderr, **kwargs)
def to_html(elem: html.HtmlElement) -> str:
"""Shorthand function to serialise a `HtmlElement` to a HTML string"""
- return html.tostring(elem, encoding="unicode") # type: ignore
- # Type checkers complain because `tostring()` formally returns `bytes`,
- # but with encoding="unicode" it actually returns a `str`.
+ return html.tostring(elem, encoding="unicode")
-def insert_grow(l: list, index: int, value: Any, fill_value: Optional[Any] = None):
+def insert_grow(l: list[Any], index: int, value: Any, fill_value: Any | None = None):
"""Insert at a given position in a list, growing it if necessary
:param l: list
diff --git a/tetras_extraction/macao_12/script/extract.py b/tetras_extraction/macao_12/script/extract.py
index 34ff07826ab8e0c4e48b8e8833292e425713a5b9..196848dd2e287857096adc9a7ae08c025f9b22ab 100644
--- a/tetras_extraction/macao_12/script/extract.py
+++ b/tetras_extraction/macao_12/script/extract.py
@@ -1,6 +1,4 @@
import filecmp
-from pprint import pprint
-from typing import Optional
from lxml import etree
from rdflib import RDFS, Graph, Literal, URIRef
@@ -80,8 +78,8 @@ def parse_manifest(graph: Graph):
def parse_manifest_rec(
graph: Graph,
elem: etree._Element,
- parentResource: Optional[URIRef] = None,
- index: Optional[int] = None,
+ parentResource: URIRef | None = None,
+ index: int | None = None,
):
"""Parses a module `MosMod` from the manifest recursively, adding all its
descendants to the `graph`
@@ -123,7 +121,7 @@ def parse_manifest_rec(
extract_mosetp.parse_mosetp(graph, f"{SOURCE_DIR}/sco/{id}.html", id)
-def compare_files(f1, f2):
+def compare_files(f1: str, f2: str):
print(
"Files {} and {} {}.".format(
f1, f2, "are identical" if filecmp.cmp(f1, f2) else "differ"
diff --git a/tetras_extraction/macao_12/script/extract_mosetp.py b/tetras_extraction/macao_12/script/extract_mosetp.py
index a68e45f9cc245962fa47b68f05deaca6e54546b1..426a5c9701f28bf2f87ecffecaacf50e77c62693 100644
--- a/tetras_extraction/macao_12/script/extract_mosetp.py
+++ b/tetras_extraction/macao_12/script/extract_mosetp.py
@@ -1,11 +1,11 @@
+from os import path
import re
import subprocess
-from os import path
-from rdflib import OWL, RDF, RDFS, Graph, Literal
+from rdflib import Graph, Literal, OWL, RDF, RDFS
-from extract_page import parse_page
from common import *
+from extract_page import parse_page
def generate_triples(
diff --git a/tetras_extraction/macao_12/script/extract_page.py b/tetras_extraction/macao_12/script/extract_page.py
index e9b2691dd66c4bc14c2d26872dedd7a205501e0d..d69f0e4a3a9eefe80fe128396336f7086d3c1829 100644
--- a/tetras_extraction/macao_12/script/extract_page.py
+++ b/tetras_extraction/macao_12/script/extract_page.py
@@ -1,15 +1,14 @@
-import re
-import sys
from abc import abstractmethod
from dataclasses import dataclass
-from pprint import pprint
-from typing import Any, List, Optional
+import re
+from typing import Any, Callable
import esprima as es
from lxml import etree, html
from lxml.etree import _Element
from lxml.html import HtmlElement
-from rdflib import RDF, Graph, Literal
+from rdflib import Graph, Literal, RDF
+from typing_extensions import override
from common import *
@@ -22,6 +21,7 @@ class Comment:
self.html: Any
self.elem: _Element
+ @override
def __repr__(self):
return str(self.__dict__)
@@ -32,18 +32,19 @@ class Activity:
"""The ID of the page this activity is in (`pg###`)"""
self.title: str = ""
"""Human-readable title of the activity"""
- self.description: Optional[str] = None
+ self.description: str | None = None
"""Description of the activity's body (HTML),
e.g. the instructions for an exercise activity"""
- self.comment_consigne: Optional[Comment] = None
+ self.comment_consigne: Comment | None = None
"""Another form of activity description but in a comment. May or may not
coexist with a regular description"""
- self.comment_success: Optional[Comment] = None
+ self.comment_success: Comment | None = None
"""Comment displayed on success, if applicable"""
- self.comments_sugg: List[Comment] = []
+ self.comments_sugg: list[Comment] = []
"""Help comments displayed on failure, if applicable"""
- self.comments_misc: List[Comment] = []
+ self.comments_misc: list[Comment] = []
"""Any other comments, if present"""
+ self.ref: URIRef
def save(self, graph: Graph):
"""Save activity data to the graph. Subclasses may override this method
@@ -120,11 +121,13 @@ class Activity:
case _:
raise NameError(name=name)
+ @override
def __repr__(self):
return self.get_name() + str(self.__dict__)
class Cours(Activity):
+ @override
def parse_html(self, root: HtmlElement):
super().parse_html(root)
# => Description
@@ -133,6 +136,7 @@ class Cours(Activity):
class Exercice(Activity):
+ @override
def parse_html(self, root: HtmlElement):
super().parse_html(root)
# => Description
@@ -144,8 +148,8 @@ class Exercice(Activity):
class Choice:
"""A possible answer for a question, correct or not"""
- def __init__(self, index=0):
- self.index: int = index
+ def __init__(self, index: int = 0):
+ self.index = index
self.is_correct: bool = False
self.html: str = ""
@@ -153,18 +157,20 @@ class Choice:
class ChoiceGroup:
def __init__(self):
self.label: str
- self.items: List[Choice]
+ self.items: list[Choice]
class ExerciceQC(Exercice):
- def __init__(self, is_qcm=False) -> None:
+ def __init__(self, is_qcm: bool = False) -> None:
super().__init__()
- self.is_qcm: bool = is_qcm
- self.choices: List[Choice] = []
+ self.is_qcm = is_qcm
+ self.choices: list[Choice] = []
+ @override
def get_name(self) -> str:
return "ExerciceQC_QCM" if self.is_qcm else "ExerciceQC_QCU"
+ @override
def parse_html(self, root: HtmlElement):
super().parse_html(root)
# Find question choices
@@ -174,6 +180,7 @@ class ExerciceQC(Exercice):
index = int(choice.attrib["id"].replace("lienRep", ""))
self.set_html(index - 1, to_html(choice).strip())
+ @override
def save(self, graph: Graph):
super().save(graph)
for choice in self.choices:
@@ -213,31 +220,32 @@ class ExerciceQC(Exercice):
class ExerciceQM(Exercice):
def __init__(self):
super().__init__()
- self.questions: List[ChoiceGroup]
+ self.questions: list[ChoiceGroup]
class ExerciceTAT(Exercice):
def __init__(self):
super().__init__()
self.text: str # can be HTML
- self.gaps: List[ChoiceGroup]
+ self.gaps: list[ChoiceGroup]
class ExerciceGD(Exercice):
def __init__(self):
super().__init__()
- self.targets: List[str]
- self.draggables: List[List[Choice]]
+ self.targets: list[str]
+ self.draggables: list[list[Choice]]
class JSParser:
@abstractmethod
- def parse(self, js, output=sys.stdout) -> Activity:
+ def parse(self, js: str) -> Activity:
"""Parse a string of JavaScript code and returns an instance of the
correct `Activity` subclass, partially populated with data found in the code.
"""
pass
+ @override
def __str__(self) -> str:
return type(self).__name__
@@ -247,7 +255,8 @@ class RegexParser(JSParser):
self.graph = graph
self.act_id = act_id
- def parse(self, js) -> Activity:
+ @override
+ def parse(self, js: str) -> Activity:
# Find function declaration and only keep code after it
func_split = re.split(r"\s*?function entrerDonnees\(\s*?\)\s*?{", js)
if len(func_split) < 2:
@@ -318,8 +327,14 @@ class XpathParser(JSParser):
'*//NewExpression/callee/Identifier[@name="Cours" or starts-with(@name, "Exercice")]'
)
- def parse(self, js) -> Activity:
- jstree = es.parseScript(js, None)
+ def __init__(self) -> None:
+ self.fun: Any
+ """AST element corresponding to the function we're interested in.
+ Initialised in `self.parse()`."""
+
+ @override
+ def parse(self, js: str) -> Activity:
+ jstree: Any = es.parseScript(js, None)
# Convert Esprima object tree to XML etree
xml = self.to_xml(jstree.toDict(), "jstree")
try:
@@ -358,7 +373,7 @@ class XpathParser(JSParser):
# "correct" or "incorrect" line
activity.set_correct(index, e.get("name") == "CODE_V")
- def to_xml(self, obj, tag_name: Optional[str] = None):
+ def to_xml(self, obj: Any, tag_name: str | None = None):
"""Recursively convert an object structure to an XML `ElementTree`.
Structures are expected to be Python dictionaries.
Converting a dictionary produces a tag named after the "type" attribute (if present).
@@ -420,10 +435,10 @@ class MatchParser(JSParser):
def __init__(self, graph: Graph, act_id: str) -> None:
self.graph = graph
self.act_id = act_id
- self.activity: Optional[Activity] = None
+ self.activity: Activity | None = None
- def parse(self, js, output=sys.stdout) -> Activity:
- self.output = output
+ @override
+ def parse(self, js: str) -> Activity:
jstree = es.parseScript(js, None)
# Try to match our template with one of the top-level statements
for statement in jstree.body:
@@ -434,7 +449,7 @@ class MatchParser(JSParser):
else:
raise ParseError("No activity constructor found")
- def match_constructor_call(self, new_expr: dict):
+ def match_constructor_call(self, new_expr: dict[str, Any]):
if self.activity is not None: # Ignore anything after the first match
return
match new_expr:
@@ -466,7 +481,7 @@ class MatchParser(JSParser):
case _:
pass
- def match_function(self, func: dict):
+ def match_function(self, func: dict[str, Any]):
"""Checks if `func` matches a function declaration named `entrerDonnees`,
and search its body if successful
"""
@@ -481,9 +496,11 @@ class MatchParser(JSParser):
for statement in body:
# Find constructor calls (e.g. `new Thing()`) recursively
recurse_prefix(statement, self.match_constructor_call)
+ case _:
+ pass
-def recurse_prefix(t, f):
+def recurse_prefix(t: Any, f: Callable[[Any], None]):
"""Depth-first prefixed recursion: calls a function on an object, then on
all its children (if it's a list or dictionary) recursively
@@ -515,7 +532,7 @@ def parse_page(graph: Graph, filepath: str, id: str):
root = tree.getroot()
# Collect all inline scripts (no external 'src') and join them in a
# block of JS code
- scripts: List[HtmlElement] = root.xpath(
+ scripts: list[HtmlElement] = root.xpath(
'/html/head/script[@type="text/javascript" and not(@src)]'
)
js = "\n".join((s.text_content() for s in scripts))
diff --git a/tetras_extraction/macao_12/script/pyrightconfig.json b/tetras_extraction/macao_12/script/pyrightconfig.json
new file mode 100644
index 0000000000000000000000000000000000000000..5f26bcacd410c0a839a66723813248d458722e6d
--- /dev/null
+++ b/tetras_extraction/macao_12/script/pyrightconfig.json
@@ -0,0 +1,14 @@
+{
+ "reportMissingTypeStubs": "information",
+ "reportUnusedCallResult": "none",
+ "reportUnusedVariable": "warning",
+ "reportUnusedImport": "warning",
+ "reportMissingParameterType": "warning",
+ "reportMissingArgumentType": "warning",
+ "reportPrivateUsage": "none" /* lxml.etree often returns _Element */,
+ "reportUnknownParameterType": "none",
+ "reportUnknownArgumentType": "none",
+ "reportUnknownVariableType": "none",
+ "reportUnknownMemberType": "none",
+ "reportAny": "none"
+}
\ No newline at end of file