xref wip

Author: ramalho

calango/pyproject.toml

@@ -7,7 +7,9 @@ authors = [
     { name = "Luciano Ramalho", email = "luciano@ramalho.org" }
 ]
 requires-python = ">=3.14"
-dependencies = []
+dependencies = [
+    "beautifulsoup4>=4.13.5",
+]
 
 [project.scripts]
 calango = "calango:main"

calango/src/calango/xrefs.py

@@ -1,5 +1,7 @@
+import xml.etree.ElementTree as ET
 from enum import Enum, auto
 from dataclasses import dataclass
+from bs4 import BeautifulSoup
 
 
 class Kind(Enum):
@@ -13,19 +15,38 @@ class Kind(Enum):
 @dataclass
 class Target:
     ident: str
-    vol: int = 0
-    chap: int = 0
-    numbers: tuple[int, ...] | None = None
+    numbers: tuple[int, ...] = ()
     kind: Kind = Kind.PART
 
     def __post_init__(self):
         self.kind = self.get_kind()
+        if self.kind is not Kind.CHAPTER:
+            return
+        self.numbers = (self.chapter, )
+
+    @property
+    def volume(self) -> int:
+        return (self.chapter - 1) // 8 + 1
+
+    @property
+    def chapter(self) -> int:
+        return CHAPTER_NUMBER[self.ident]
 
     def get_kind(self) -> Kind:
         if self.ident.startswith('ch_'):
             return Kind.CHAPTER
+        elif self.ident.endswith('_sec'):
+            return Kind.SECTION
         raise ValueError(f'Kind of {self.ident!r} is unknown')
 
+    def get_section_title(self, root: BeautifulSoup) -> str:
+        element = root.find(id=self.ident)    
+        if element:
+            return element.get_text(strip=True)
+        raise LookupError(f'element {self.ident} not found')
+
+        
+
 
 def validate(xref):
     return any([
@@ -34,4 +55,34 @@ def validate(xref):
         xref.endswith('_sec'),
         xref.endswith('_part'),
         xref.endswith('_tbl'),
-    ])
+    ])
+
+CHAPTER_ID = {
+    1 : 'ch_data_model',
+    2 : 'ch_sequences',
+    3 : 'ch_dicts_sets',
+    4 : 'ch_str_bytes',
+    5 : 'ch_dataclass',
+    6 : 'ch_refs_mut_mem',
+    7 : 'ch_func_objects',
+    8 : 'ch_type_hints_def',
+    9 : 'ch_closure_decorator',
+    10 : 'ch_design_patterns',
+    11 : 'ch_pythonic_obj',
+    12 : 'ch_seq_methods',
+    13 : 'ch_ifaces_prot_abc',
+    14 : 'ch_inheritance',
+    15 : 'ch_more_types',
+    16 : 'ch_op_overload',
+    17 : 'ch_generators',
+    18 : 'ch_with_match',
+    19 : 'ch_concurrency_models',
+    20 : 'ch_executors',
+    21 : 'ch_async',
+    22 : 'ch_dynamic_attrs',
+    23 : 'ch_descriptors',
+    24 : 'ch_class_metaprog',
+}
+
+CHAPTER_NUMBER = {i:n for (n, i) in CHAPTER_ID.items()}
+

calango/tests/test_xrefs.py

@@ -1,8 +1,33 @@
 import pytest
 from calango.xrefs import Target, Kind
+from bs4 import BeautifulSoup
 
-def test_recursion_depth():
+@pytest.mark.parametrize('ident, expected', [
+    ('ch_data_model', Kind.CHAPTER),
+    ('data_model_emulating_sec', Kind.SECTION)
+])
+def test_kind(ident, expected):
+    target = Target(ident)
+    assert target.kind == expected
+
+@pytest.mark.parametrize('ident, expected', [
+    ('ch_data_model', (1, 1)),
+    ('ch_seq_methods', (2, 12)),
+    ('ch_descriptors', (3, 23)),
+    ('data_model_emulating_sec', (1, 1))
+])
+def test_volume_and_chapter(ident, expected):
+    target = Target(ident)
+    assert target.volume, target.chapter == expected
+
+def test_unknown_kind():
     with pytest.raises(ValueError) as excinfo:
-        _ = Target('something')
+        Target('something')
+
+    assert "Kind of 'something' is unknown" in str(excinfo.value)
 
-    assert "Kind of 'something' is unknown" in str(excinfo.value)
+def test_get_section_title():
+    html = '''<h3 id="typeddict_sec"><a class="link" href="#typeddict_sec">15.3. TypedDict</a></h3>'''
+    root = BeautifulSoup(html, 'html.parser')
+    target = Target('typeddict_sec')
+    assert target.get_section_title(root) == '15.3. TypedDict'

calango/uv.lock

@@ -16,7 +16,7 @@ def main(adoc_names):
         for line in lines:
             if line.startswith('[['):
                 ch_id = line.strip()[2:-2]
-                print(vol_of_chapter(ch), ch, ch_id, sep='\t')
+                print(f'    {ch} : {ch_id!r},')
                 break
 
 if __name__ == '__main__':