tds3p-rsvp-reader/tests/test_epub_to_chapters.py

import tempfile
import unittest
from pathlib import Path

from bs4 import BeautifulSoup

from epub_to_chapters import (
    SIDECAR_HEADER,
    SIDECAR_MAGIC,
    SIDECAR_VERSION,
    STYLE_BOLD,
    STYLE_ITALIC,
    decode_styled_text,
    document_root,
    html_to_text,
    normalize_display_text,
    normalize_text,
    output_section_name,
    parse_document,
    source_fingerprint,
    stylesheet_class_styles,
    write_style_sidecar,
    write_conversion_report,
)


class DisplayTextNormalizationTests(unittest.TestCase):
    def test_converts_ligatures_accents_and_supported_symbols_to_ascii(self):
        source = (
            "\ufb01 \ufb02 \ufb03 caf\u00e9 \u00c5ngstr\u00f6m sm\u00f8rrebr\u00f8d "
            "Stra\u00dfe \u0153uvre \u0141\u00f3d\u017a \u00bd \u2260 \u2022 \u2042"
        )

        self.assertEqual(
            normalize_display_text(source),
            "fi fl ffi cafe Angstrom smorrebrod Strasse oeuvre Lodz 1/2 != * ***",
        )

    def test_handles_unicode_whitespace_and_invisible_formatting(self):
        source = "one\u00a0two\u200bthree\u200et\u200f four"

        self.assertEqual(
            normalize_display_text(source),
            "one two threet four",
        )

    def test_em_dash_retains_an_rsvp_token_boundary(self):
        self.assertEqual(normalize_text("left\u2014right"), "left- right")

    def test_section_names_use_the_same_normalization(self):
        used_names = set()

        self.assertEqual(
            output_section_name("Caf\u00e9 \u2014 Part \u00bd", 1, used_names),
            "Cafe - Part 1-2",
        )


class ConversionReportTests(unittest.TestCase):
    def test_reports_remaining_non_ascii_characters_by_generated_file(self):
        with tempfile.TemporaryDirectory() as temporary_directory:
            report_file, has_unsupported = write_conversion_report(
                Path(temporary_directory),
                ["Chapter \u03a9"],
                [("Chapter \u03a9.txt", "\u3053\u3093\u306b\u3061\u306f")],
            )

            report = report_file.read_text(encoding="utf-8")

        self.assertTrue(has_unsupported)
        self.assertIn("U+03A9 GREEK CAPITAL LETTER OMEGA", report)
        self.assertIn("U+3053 HIRAGANA LETTER KO", report)
        self.assertIn("TOC.txt", report)

    def test_reports_an_ascii_safe_conversion(self):
        with tempfile.TemporaryDirectory() as temporary_directory:
            report_file, has_unsupported = write_conversion_report(
                Path(temporary_directory),
                ["Chapter 1"],
                [("Chapter 1.txt", "Plain ASCII text.")],
            )

            report = report_file.read_text(encoding="utf-8")

        self.assertFalse(has_unsupported)
        self.assertIn("all generated TOC and chapter text is ASCII-safe", report)


class StyleSidecarTests(unittest.TestCase):
    def test_extracts_italic_and_bold_word_styles(self):
        soup = BeautifulSoup(
            "<p>plain <i>italic</i> <strong>bold</strong> "
            "<em><b>both</b></em></p>",
            "html.parser",
        )

        text, records = decode_styled_text(html_to_text(document_root(soup)))

        self.assertEqual(text, "plain italic bold both")
        self.assertEqual(
            records,
            [
                (1, STYLE_ITALIC, 0),
                (2, STYLE_BOLD, 0),
                (3, STYLE_ITALIC | STYLE_BOLD, 0),
            ],
        )

    def test_writes_a_versioned_sidecar_with_source_fingerprint(self):
        text = "plain italic bold both"
        records = [
            (1, STYLE_ITALIC, 0),
            (2, STYLE_BOLD, 0),
            (3, STYLE_ITALIC | STYLE_BOLD, 0),
        ]

        with tempfile.TemporaryDirectory() as temporary_directory:
            sidecar_file = Path(temporary_directory) / "Chapter 1.rsvp"
            write_style_sidecar(sidecar_file, text, records)
            data = sidecar_file.read_bytes()

        magic, version, reserved, fingerprint, record_count = SIDECAR_HEADER.unpack(
            data[:SIDECAR_HEADER.size]
        )
        self.assertEqual(magic, SIDECAR_MAGIC)
        self.assertEqual(version, SIDECAR_VERSION)
        self.assertEqual(reserved, 0)
        self.assertEqual(fingerprint, source_fingerprint(text))
        self.assertEqual(record_count, len(records))
        self.assertEqual(
            data[SIDECAR_HEADER.size:],
            bytes([
                1, STYLE_ITALIC, 0,
                1, STYLE_BOLD, 0,
                1, STYLE_ITALIC | STYLE_BOLD, 0,
            ]),
        )

    def test_extracts_styles_from_css_classes_and_inline_css(self):
        class FakeItem:
            def __init__(self, name, content):
                self.file_name = name
                self._content = content.encode("utf-8")

            def get_name(self):
                return self.file_name

            def get_content(self):
                return self._content

        class FakeBook:
            def __init__(self, items):
                self._items = items

            def get_items(self):
                return self._items

        stylesheet = FakeItem(
            "stylesheet.css",
            ".voice { font-style: italic; }\n"
            ".both { font: italic 700 1em serif; }",
        )
        document = FakeItem(
            "chapter.xhtml",
            "<p>Plain <span class='voice'>italic words</span> "
            "<span style='font-weight: bold'>bold words</span> "
            "<span class='both'>both</span></p>",
        )

        class_styles = stylesheet_class_styles(FakeBook([stylesheet, document]))
        soup = parse_document(document, class_styles)
        text, records = decode_styled_text(html_to_text(document_root(soup)))

        self.assertEqual(text, "Plain italic words bold words both")
        self.assertEqual(
            records,
            [
                (1, STYLE_ITALIC, 0),
                (2, STYLE_ITALIC, 0),
                (3, STYLE_BOLD, 0),
                (4, STYLE_BOLD, 0),
                (5, STYLE_ITALIC | STYLE_BOLD, 0),
            ],
        )


if __name__ == "__main__":
    unittest.main()