feat: Sprachlabels für Codeblöcke aus Inhalt und Buchkontext (R1)

- Gedruckte Zeilennummern ("00  #include …") werden für die Erkennung
  ignoriert, bleiben aber im Block stehen.
- Python zusätzlich per ast.parse (Kontrollstrukturen, def/class, Import
  mit Code) und an >>>-Sitzungen erkannt; YAML zählt nicht.
- Vordurchlauf bestimmt die Sprache des Buches aus den sicher erkannten
  Blöcken; passt sie, reichen für kurze Schnipsel schwächere Signale
  (detected_by: "book-context"). Programmausgaben bleiben ohne Label.

Ohne Label: C-Buch 518 -> 132 von 574, Python-Buch 492 -> 326 von 747.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_codeblocks.py

@@ -118,3 +118,57 @@ def test_print_wrap_markers_can_be_kept(convert):
     run = convert(Book(docs=[Doc("c.xhtml", body)]), "--keep-wrap-markers")
     (_, _, code), = fenced_blocks(run.chapter("001"))
     assert code == "a = (1,\n↪ 2)"
+
+
+def test_printed_line_numbers_do_not_hide_the_language(convert):
+    listing = ("00  // Kapitel1/hallo.c\n01  #include <stdio.h>\n \n02  int main(void) {\n"
+               "03    printf(\"Hallo\\n\");\n04    return 0;\n05  }")
+    run = convert(Book(docs=[Doc("c.xhtml", f"<h1>N</h1><pre>{listing}</pre>")]))
+    (_, lang, code), = fenced_blocks(run.chapter("001"))
+    assert lang == "c"
+    assert code.startswith("00  // Kapitel1/hallo.c\n01  #include <stdio.h>")  # numbers stay in the block
+
+
+def test_python_is_recognized_by_parsing(convert):
+    blocks = ["from collections import ChainMap\n\nchain = ChainMap({}, {})\nprint(chain)",
+              "zahl = -1\nif zahl &lt; 0:\n    print(\"negativ\")",
+              "&gt;&gt;&gt; 2 + 3\n5",
+              "name: epub2md\nversion: 1",  # YAML is valid Python syntax, but no Python code
+              "[1, 4, 9]",  # program output
+              "x = compute()"]  # Python, but too weak without book context
+    body = "<h1>P</h1>" + "".join(f"<pre>{b}</pre>" for b in blocks)
+    run = convert(Book(docs=[Doc("c.xhtml", body)]))
+    langs = [lang for _, lang, _ in fenced_blocks(run.chapter("001"))]
+    assert langs == ["python", "python", "python", "", "", ""]
+
+
+def test_weak_signals_follow_the_book_language(convert):
+    c_listing = "#include &lt;stdio.h&gt;\nint main(void) { return 0; }"
+    snippets = ["char ch = 65;  // 'A'", "if (a || b) {\n  x();\n}", "int remove(const char *pathname);",
+                "struct node {\n  int value;\n};", "Ergebnis: 12345", "|00003.14|", "gcc -Wall -o prog prog.c",
+                "Dezimal: 65; Zeichen: A"]
+    body = "<h1>C</h1>" + "".join(f"<pre>{c_listing}</pre>" for _ in range(5))
+    body += "".join(f"<pre>{s}</pre>" for s in snippets)
+    run = convert(Book(docs=[Doc("c.xhtml", body)]))
+    langs = [lang for _, lang, _ in fenced_blocks(run.chapter("001"))][5:]
+    assert langs == ["c", "c", "c", "c", "", "", "", ""]
+    by = [item["detected_by"] for item in run.report["code_blocks"]["items"]][5:9]
+    assert by == ["book-context"] * 4
+
+
+def test_python_book_labels_assignments_but_not_output(convert):
+    py = "def f(x):\n    return x"
+    snippets = ["foo = decorate(foo)", "random.sample(population, k)", "[x * x for x in range(5)]",
+                "True", "('A', 'B', 'C')", "Hallo Welt", "4\n3\nnohtyP", "Jane\n42\nPerson(name='Jane')"]
+    body = "<h1>P</h1>" + "".join(f"<pre>{py}</pre>" for _ in range(5))
+    body += "".join(f"<pre>{s}</pre>" for s in snippets)
+    run = convert(Book(docs=[Doc("c.xhtml", body)]))
+    langs = [lang for _, lang, _ in fenced_blocks(run.chapter("001"))][5:]
+    assert langs == ["python", "python", "python", "", "", "", "", ""]
+
+
+def test_mixed_book_gets_no_context_labels(convert):
+    body = "<h1>M</h1>" + "<pre>def f(x):\n    return x</pre>" * 3
+    body += "<pre>#include &lt;stdio.h&gt;\nint main(void) { return 0; }</pre>" * 3 + "<pre>x = compute();</pre>"
+    run = convert(Book(docs=[Doc("c.xhtml", body)]))
+    assert fenced_blocks(run.chapter("001"))[-1][1] == ""

tests/test_qa2_open.py

@@ -39,7 +39,7 @@ def test_qa2_10_book_readme_recommends_pdf_via_html(convert):
 
 def test_qa2_11_code_language_hint(convert):
     py = "def f(x):\n    return x\n\nclass A:\n    pass"
-    body = "<h1>C</h1>" + "".join(f"<pre>{py}\n# {i}</pre><pre>print({i})</pre>" for i in range(10))
+    body = "<h1>C</h1>" + "".join(f"<pre>{py}\n# {i}</pre><pre>Ergebnis: {i}</pre>" for i in range(10))
     run = convert(Book(docs=[Doc("c.xhtml", body)]))
     hints = [i for i in run.report["infos"] if i["code"] == "code-language-hint"]
     assert hints and "--code-language python" in hints[0]["message"]