epub2md/tests/test_codeblocks.py

import re

from conftest import Book, Doc

PY = """def read_book(path):
    if path:
        return path.read_text(encoding="utf-8")  # <utf-8>
\treturn None"""


def fenced_blocks(text: str) -> list[tuple[str, str]]:
    return re.findall(r"^(`{3,})([\w+-]*)\n(.*?)\n\1$", text, re.M | re.S)


def test_python_indentation_and_special_chars(convert):
    body = f'<h1>Code</h1><pre><code class="language-python">{PY}</code></pre>'
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    blocks = fenced_blocks(run.chapter("001"))
    assert len(blocks) == 1
    fence, lang, code = blocks[0]
    assert lang == "python"
    assert code == PY.replace("&lt;", "<").replace("&gt;", ">")
    assert "&lt;" not in code


def test_shell_code_with_pipes_backslashes_and_dollar(convert):
    shell = "$ cat datei.txt | grep -v '^#' \\\n    | sort &amp;&amp; echo \"$HOME\" > out.txt"
    body = f"<h1>Shell</h1><pre>{shell}</pre>"
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (_, lang, code), = fenced_blocks(run.chapter("001"))
    assert code == "$ cat datei.txt | grep -v '^#' \\\n    | sort && echo \"$HOME\" > out.txt"
    assert lang == ""  # no reliable language signal -> no label


def test_backticks_in_code_get_longer_fence(convert):
    body = "<h1>T</h1><pre>echo ```nested``` and `x`</pre>"
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (fence, _, code), = fenced_blocks(run.chapter("001"))
    assert fence == "````"
    assert code == "echo ```nested``` and `x`"


def test_br_lines_and_highlight_spans_in_pre(convert):
    body = ('<h1>C</h1><div class="listing"><pre><span class="kw">#include</span> &lt;stdio.h&gt;<br/><br/>'
            'int main(void) {<br/>   printf("Hallo\\n");<br/>} </pre></div>')
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (_, lang, code), = fenced_blocks(run.chapter("001"))
    assert lang == "c"
    assert code == '#include <stdio.h>\n\nint main(void) {\n   printf("Hallo\\n");\n} '


def test_listing_div_with_span_pre(convert):
    body = ('<h1>K</h1><div class="divUnProgramlisting"><span class="pre"><strong>def</strong> f(x):\n'
            '    <strong>return</strong> 2 * x\n\n<strong>def</strong> g(x):\n    <strong>return</strong> x</span></div>')
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (_, lang, code), = fenced_blocks(run.chapter("001"))
    assert lang == "python"
    assert code == "def f(x):\n    return 2 * x\n\ndef g(x):\n    return x"


def test_line_numbers_are_removed(convert):
    body = '<h1>L</h1><pre><span class="lineno">1</span>a = 1<br/><span class="lineno">2</span>b = 2</pre>'
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (_, _, code), = fenced_blocks(run.chapter("001"))
    assert code == "a = 1\nb = 2"


def test_inline_code_variants(convert):
    body = ('<h1>I</h1><p>Nutze <code>a*b_c</code>, <span class="tt">x | y</span> und <code>`tick`</code> '
            'sowie <kbd>Strg</kbd>.</p>')
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    text = run.chapter("001")
    assert "`a*b_c`" in text
    assert "`x | y`" in text
    assert "`` `tick` ``" in text
    assert "<kbd>Strg</kbd>" in text


def test_prose_is_not_forced_into_code(convert):
    body = "<h1>P</h1><p>Ein normaler Absatz mit    Leerzeichen.</p>"
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    assert "```" not in run.chapter("001")
    assert "Ein normaler Absatz mit Leerzeichen." in run.chapter("001")


def test_unlabeled_code_is_reported(convert):
    run = convert(Book(docs=[Doc("c.xhtml", "<h1>U</h1><pre>foo bar</pre>")]))
    assert run.report["code_blocks"]["languages"] == {"(keine)": 1}


def test_code_language_option_fills_only_unlabeled_blocks(convert):
    body = "<h1>C</h1><pre>x = compute()</pre><pre>#include &lt;stdio.h&gt;\nint main(void) { return 0; }</pre>"
    run = convert(Book(docs=[Doc("c.xhtml", body)]), "--code-language", "py")
    langs = [lang for _, lang, _ in fenced_blocks(run.chapter("001"))]
    assert langs == ["python", "c"]
    by = {item["language"]: item["detected_by"] for item in run.report["code_blocks"]["items"]}
    assert by == {"python": "option", "c": "content"}


def test_code_language_option_rejects_unknown_values(convert):
    run = convert(Book(docs=[Doc("c.xhtml", "<h1>C</h1><pre>x</pre>")]), "--code-language", "quatsch")
    assert run.rc == 1
    assert "quatsch" in run.stderr


def test_print_wrap_markers_are_joined(convert):
    body = ("<h1>W</h1><pre>    return (s * (s -\n    ↪ distance(a, b)) *\n        s)\n"
            "x = ['a', 'b',\n↪ 'c']</pre>")
    run = convert(Book(docs=[Doc("c.xhtml", body)]))
    (_, _, code), = fenced_blocks(run.chapter("001"))
    assert code == "    return (s * (s - distance(a, b)) *\n        s)\nx = ['a', 'b', 'c']"
    item = run.report["code_blocks"]["items"][0]
    assert item["wrap_lines_joined"] == 2


def test_print_wrap_markers_can_be_kept(convert):
    body = "<h1>W</h1><pre>a = (1,\n↪ 2)</pre>"
    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 &lt;stdio.h&gt;\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] == ""