updated with functional changes, testing

pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+pythonpath = src
+testpaths = tests

requirements.txt

@@ -0,0 +1 @@
+pytest

src/epubmaker/cli.py

@@ -1,50 +1,45 @@
 import os
 import argparse
 from datetime import datetime
-from . import state
+from .models import BuildContext
-from .models import Book
+from .parser import parse_book
-from .parser import parseBook
 from .writer import (
-    writeStructure, writeMisc, writeStyles, writeNCX,
+    write_structure, write_misc, write_styles, write_ncx,
-    writeCover, writeContents, writeSections, writeIllustrations, writeEpub,
+    write_cover, write_contents, write_sections, write_illustrations, write_epub,
 )
 
 
-def parseArgs():
+def parse_args(ctx: BuildContext) -> bool:
     parser = argparse.ArgumentParser()
     parser.add_argument("fileName", help="File to process")
     parser.add_argument("-f", "--force", help="Force overwrite an existing book directory", action="store_true")
     parser.add_argument("-v", "--verbose", help="Provide updates while processing", action="store_true")
     args = parser.parse_args()
-    state.book.filename = str(args.fileName)
+    ctx.book.filename = str(args.fileName)
-    if not os.path.isfile(state.book.filename):
+    if not os.path.isfile(ctx.book.filename):
-        print("File '{}' is not found. Exiting...".format(state.book.filename))
+        print("File '{}' is not found. Exiting...".format(ctx.book.filename))
         exit()
-    state.verbose = args.verbose
+    ctx.verbose = args.verbose
     return args.force
 
 
-def main():
+def main() -> None:
-    state.book = Book()
+    ctx = BuildContext()
-    state.book.publishDate = (
+    ctx.book.publish_date = "{}-{}-{}".format(
-        str(datetime.now().year) + "-" +
+        datetime.now().year,
-        str(datetime.now().month) + "-" +
+        datetime.now().month,
-        str(datetime.now().day)
+        datetime.now().day,
     )
-    state.inSection = False
+    overwrite = parse_args(ctx)
-    state.inStyle = False
+    parse_book(ctx)
-    state.verbose = False
+    if overwrite and ctx.verbose:
-
-    overwrite = parseArgs()
-    parseBook()
-    if overwrite and state.verbose:
         print("Force flag, overwriting existing directory")
-    writeStructure(overwrite)
+    write_structure(ctx, overwrite)
-    writeMisc()
+    write_misc(ctx)
-    writeStyles()
+    write_styles(ctx)
-    writeNCX()
+    write_ncx(ctx)
-    writeCover()
+    write_cover(ctx)
-    writeContents()
+    write_contents(ctx)
-    writeSections()
+    write_sections(ctx)
-    writeIllustrations()
+    write_illustrations(ctx)
-    writeEpub()
+    write_epub(ctx)

src/epubmaker/models.py

@@ -1,49 +1,60 @@
+from dataclasses import dataclass, field
+from typing import List
+
+
+@dataclass
 class Name:
-    def __init__(self):
+    first: str = ""
-        self.first = ""
+    last: str = ""
-        self.last = ""
 
 
+@dataclass
 class Series:
-    def __init__(self):
+    number: str = ""
-        self.number = ""
+    name: str = ""
-        self.name = ""
 
 
+@dataclass
 class Image:
-    def __init__(self):
+    name: str = ""
-        self.name = ""
+    type: str = ""
-        self.type = ""
+    alt: str = ""
-        self.alt = ""
+    caption: str = ""
-        self.caption = ""
 
 
+@dataclass
 class Section:
-    def __init__(self):
+    type: str = ""
-        self.type = ""
+    name: str = ""
-        self.name = ""
+    title: str = ""
-        self.title = ""
+    body: str = ""
-        self.body = ""
 
 
+@dataclass
 class Book:
-    def __init__(self):
+    filename: str = ""
-        self.filename = ""
+    title: str = ""
-        self.title = ""
+    titlesort: str = ""
-        self.titlesort = ""
+    series: Series = field(default_factory=Series)
-        self.series = Series()
+    author: List[Name] = field(default_factory=list)
-        self.author = []
+    artist: Name = field(default_factory=Name)
-        self.artist = Name()
+    editor: Name = field(default_factory=Name)
-        self.editor = Name()
+    publisher: str = ""
-        self.publisher = ""
+    copyright: str = ""
-        self.copyright = ""
+    subjects: str = ""
-        self.subjects = ""
+    style: str = ""
-        self.style = ""
+    directory: str = ""
-        self.directory = ""
+    isbn: str = ""
-        self.isbn = ""
+    uuid: str = ""
-        self.uuid = ""
+    source: str = ""
-        self.source = ""
+    images: List[Image] = field(default_factory=list)
-        self.images = []
+    sections: List[Section] = field(default_factory=list)
-        self.sections = []
+    cover: Image = field(default_factory=Image)
-        self.cover = Image()
+    publish_date: str = ""
-        self.publishDate = ""
+
+
+@dataclass
+class BuildContext:
+    book: Book = field(default_factory=Book)
+    verbose: bool = False
+    in_section: bool = False

src/epubmaker/parser.py

@@ -1,174 +1,156 @@
 from uuid import uuid4
-from . import state
+from .models import Name, Image, Section, BuildContext
-from .models import Name, Image, Section
 
 
-def extract(line):
+def extract(line: str) -> str | None:
     if line.startswith("<!-- "):
         return line[5:-4]
+    return None
 
 
-def identify(line):
+def identify(line: str, ctx: BuildContext) -> None:
     key, value = extract(line).split(" ", 1)
     match key:
         case "Directory:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.directory = value.strip()
+            ctx.book.directory = value.strip()
         case "Title:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.title = value.strip()
+            ctx.book.title = value.strip()
-            if state.book.title.startswith("A "):
+            if ctx.book.title.startswith("A "):
-                state.book.titlesort = state.book.title[2:] + ", " + state.book.title[:1]
+                ctx.book.titlesort = ctx.book.title[2:] + ", " + ctx.book.title[:1]
-            if state.book.title.startswith("An "):
+            if ctx.book.title.startswith("An "):
-                state.book.titlesort = state.book.title[3:] + ", " + state.book.title[:2]
+                ctx.book.titlesort = ctx.book.title[3:] + ", " + ctx.book.title[:2]
-            if state.book.title.startswith("The "):
+            if ctx.book.title.startswith("The "):
-                state.book.titlesort = state.book.title[4:] + ", " + state.book.title[:3]
+                ctx.book.titlesort = ctx.book.title[4:] + ", " + ctx.book.title[:3]
         case "Titlesort":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.titlesort = value.strip()
+            ctx.book.titlesort = value.strip()
         case "Author:":
-            state.inSection = False
+            ctx.in_section = False
-            last, first = value.strip().split(', ')
+            last, first = value.strip().split(", ")
-            name = Name()
+            ctx.book.author.append(Name(first=first, last=last))
-            name.first = first
-            name.last = last
-            state.book.author.append(name)
         case "Editor:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.editor.last, state.book.editor.first = value.strip().split(', ')
+            ctx.book.editor.last, ctx.book.editor.first = value.strip().split(", ")
         case "Artist:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.artist.last, state.book.artist.first = value.strip().split(', ')
+            ctx.book.artist.last, ctx.book.artist.first = value.strip().split(", ")
         case "Publisher:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.publisher = value.strip()
+            ctx.book.publisher = value.strip()
         case "Copyright:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.copyright = value.strip()
+            ctx.book.copyright = value.strip()
         case "ISBN:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.isbn = value.strip()
+            ctx.book.isbn = value.strip()
         case "UUID:":
-            state.inSection = False
+            ctx.in_section = False
-            if value.strip() == "":
+            ctx.book.uuid = str(uuid4()) if value.strip() == "" else value.strip()
-                state.book.uuid = uuid4()
-            else:
-                state.book.uuid = value.strip()
         case "Source:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.source = value.strip()
+            ctx.book.source = value.strip()
         case "Subjects:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.subjects = value.strip()
+            ctx.book.subjects = value.strip()
         case "Series:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.series.number, state.book.series.name = value.strip().split(' ', 1)
+            ctx.book.series.number, ctx.book.series.name = value.strip().split(" ", 1)
         case "Cover:":
-            state.inSection = False
+            ctx.in_section = False
-            state.book.cover.name, state.book.cover.type = value.strip().split('.')
+            ctx.book.cover.name, ctx.book.cover.type = value.strip().split(".")
         case "TitlePage:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="title")
-            section.type = "title"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "CopyrightPage:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="copyright-page")
-            section.type = "copyright-page"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Dedication:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="dedication")
-            section.type = "dedication"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Text:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="text")
-            section.type = "text"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Foreward:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="forward")
-            section.type = "forward"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Notes:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="notes")
-            section.type = "notes"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "License:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="license")
-            section.type = "license"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Acknowledgement:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="acknowledgement")
-            section.type = "acknowledgement"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "TOC:":
-            state.inSection = True
+            ctx.in_section = True
-            section = Section()
+            section = Section(type="toc")
-            section.type = "toc"
+            section.name, section.title = value.strip().split(" ", 1)
-            section.name, section.title = value.strip().split(' ', 1)
+            ctx.book.sections.append(section)
-            state.book.sections.append(section)
         case "Image:":
             image = Image()
-            image.name, imageText = value.strip().split(' ', 1)
+            image.name, image_text = value.strip().split(" ", 1)
-            extension = image.name.strip().split('.')[1]
+            extension = image.name.strip().split(".")[1]
             match extension:
-                case "jpg":
+                case "jpg" | "jpeg":
-                    image.type = "jpeg"
-                case "jpeg":
                     image.type = "jpeg"
                 case "png":
                     image.type = "png"
-            image.alt, image.caption = imageText.strip().split('::')
+            image.alt, image.caption = image_text.strip().split("::")
-            state.book.images.append(image)
+            ctx.book.images.append(image)
             if not image.caption:
-                imageCode = '<img src="../Images/' + image.name + '" alt="' + image.alt + '"/>\n'
+                image_code = '<img src="../Images/' + image.name + '" alt="' + image.alt + '"/>\n'
-                imageCode += '    <a id="' + image.name.split('.')[0] + '"><!-- Anchor --></a>\n'
+                image_code += '    <a id="' + image.name.split(".")[0] + '"><!-- Anchor --></a>\n'
             else:
-                imageCode = '<div class="center group">\n'
+                image_code = '<div class="center group">\n'
-                imageCode += '    <img src="../Images/' + image.name + '" alt="' + image.alt + '" />\n'
+                image_code += '    <img src="../Images/' + image.name + '" alt="' + image.alt + '" />\n'
-                imageCode += '    <a id="' + image.name.split('.')[0] + '"><!-- Anchor --></a>\n'
+                image_code += '    <a id="' + image.name.split(".")[0] + '"><!-- Anchor --></a>\n'
-                imageCode += '    <p class="caption">' + image.caption + '</p>\n'
+                image_code += '    <p class="caption">' + image.caption + "</p>\n"
-                imageCode += '</div>\n<br />\n'
+                image_code += "</div>\n<br />\n"
-            state.book.sections[-1].body += imageCode
+            ctx.book.sections[-1].body += image_code
         case _:
             pass
 
 
-def findStyle(line):
+def find_style(line: str, ctx: BuildContext) -> None:
-    stylesheetFile = line.split(' ')[2].split('=')[1].replace('"', '').replace('>', '').strip()
+    stylesheet_file = line.split(" ")[2].split("=")[1].replace('"', "").replace(">", "").strip()
     contents = ""
-    with open(stylesheetFile) as file:
+    with open(stylesheet_file) as f:
-        for line in file:
+        for line in f:
-            if line != '<style>\n' and line != '</style>' and not line.strip().startswith("/*"):
+            if line != "<style>\n" and line != "</style>" and not line.strip().startswith("/*"):
                 contents += line
-    state.book.style = contents
+    ctx.book.style = contents
     print("found style")
 
 
-def parseBook():
+def parse_book(ctx: BuildContext) -> None:
-    filename = state.book.filename
+    if ctx.verbose:
-    if state.verbose:
+        print("Parsing {}".format(ctx.book.filename))
-        print("Parsing {}".format(filename))
+    with open(ctx.book.filename) as source:
-    with open(filename) as source:
         for line in source:
-            if line.startswith('<!-- '):
+            if line.startswith("<!-- "):
-                identify(line)
+                identify(line, ctx)
             elif line.startswith('<link rel="stylesheet"'):
-                findStyle(line)
+                find_style(line, ctx)
-            elif state.inSection:
+            elif ctx.in_section:
-                state.book.sections[-1].body += line
+                ctx.book.sections[-1].body += line
-    if state.verbose:
+    if ctx.verbose:
-        print("Parse complete for {}".format(state.book.title))
+        print("Parse complete for {}".format(ctx.book.title))

src/epubmaker/state.py

@@ -1,4 +0,0 @@
-book = None
-inSection = False
-inStyle = False
-verbose = False

src/epubmaker/writer.py

@@ -1,202 +1,202 @@
 import os
 import subprocess
 from shutil import rmtree, copy
-from . import state
+from .models import BuildContext
 
 
-def writeStructure(overwrite):
+def write_structure(ctx: BuildContext, overwrite: bool) -> None:
     mode = 0o775
 
-    if os.path.isdir(state.book.directory):
+    if os.path.isdir(ctx.book.directory):
         if overwrite:
-            rmtree(state.book.directory)
+            rmtree(ctx.book.directory)
         else:
-            print("writeStructure: Directory exists.")
+            print("write_structure: Directory exists.")
             exit()
 
-    os.mkdir(state.book.directory, mode)
+    os.mkdir(ctx.book.directory, mode)
 
     for directory in ["META-INF", "OEBPS", "OEBPS/Images", "OEBPS/Styles", "OEBPS/Text"]:
-        path = os.path.join(state.book.directory, directory)
+        os.mkdir(os.path.join(ctx.book.directory, directory), mode)
-        os.mkdir(path, mode)
+
-    if state.verbose:
+    if ctx.verbose:
         print("Finished writing ePub structure")
 
 
-def writeMisc():
+def write_misc(ctx: BuildContext) -> None:
-    access = 'w'
+    directory = ctx.book.directory
-    directory = state.book.directory
 
-    file = os.path.join(state.book.directory, "mimetype")
+    with open(os.path.join(directory, "mimetype"), "w") as f:
-    mimetype = open(file, access)
+        f.write("application/epub+zip")
-    mimetype.write("application/epub+zip")
-    mimetype.close()
 
-    file = os.path.join(directory, "META-INF", "com.apple.ibooks.display-options.xml")
+    with open(os.path.join(directory, "META-INF", "com.apple.ibooks.display-options.xml"), "w") as f:
-    meta1 = open(file, access)
+        f.write(
-    meta1.write('<?xml version="1.0" encoding="UTF-8"?>\n<display_options>\n  <platform name="*">\n    <option name="specified-fonts">false</option>\n  </platform>\n</display_options>')
+            '<?xml version="1.0" encoding="UTF-8"?>\n'
-    meta1.close()
+            "<display_options>\n"
+            '  <platform name="*">\n'
+            '    <option name="specified-fonts">false</option>\n'
+            "  </platform>\n"
+            "</display_options>"
+        )
 
-    file = os.path.join(directory, "META-INF", "container.xml")
+    with open(os.path.join(directory, "META-INF", "container.xml"), "w") as f:
-    meta2 = open(file, access)
+        f.write(
-    meta2.write('<?xml version="1.0" encoding="UTF-8"?>\n<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">\n  <rootfiles>\n    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>\n  </rootfiles>\n</container>')
+            '<?xml version="1.0" encoding="UTF-8"?>\n'
-    meta2.close()
+            '<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">\n'
-    if state.verbose:
+            "  <rootfiles>\n"
+            '    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>\n'
+            "  </rootfiles>\n"
+            "</container>"
+        )
+
+    if ctx.verbose:
         print("Finished writing metadata")
 
 
-def writeStyles():
+def write_styles(ctx: BuildContext) -> None:
-    access = 'w'
+    with open(os.path.join(ctx.book.directory, "OEBPS", "Styles", "style.css"), "w") as f:
-    file = os.path.join(state.book.directory, "OEBPS", "Styles", "style.css")
+        f.write(ctx.book.style)
-    style = open(file, access)
-    style.write(state.book.style)
-    style.close()
 
-    source_dir = os.path.split(state.book.filename)[0]
+    source_dir = os.path.split(ctx.book.filename)[0]
-    styles_dir = os.path.join(state.book.directory, "OEBPS", "Styles")
+    styles_dir = os.path.join(ctx.book.directory, "OEBPS", "Styles")
     for font in ["Inconsolata-Regular.otf", "invisible1.ttf", "MgOpenModataRegular.ttf"]:
         copy(os.path.join(source_dir, "Images", font), os.path.join(styles_dir, font))
 
-    if state.verbose:
+    if ctx.verbose:
         print("Finished writing style")
 
 
-def writeNCX():
+def write_ncx(ctx: BuildContext) -> None:
-    directory = state.book.directory
-    access = 'w'
-    file = os.path.join(directory, 'OEBPS', 'toc.ncx')
     navpoints = []
-
-    contentsstart = (
-        '<?xml version="1.0" encoding="UTF-8" standalone="no" ?>\n'
-        '<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN" "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">\n'
-        '<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1">\n'
-        '  <head>\n'
-        '    <meta content="urn:isbn:' + str(state.book.uuid) + '" name="dtb:uid"/>\n'
-        '    <meta content="1" name="dtb:depth"/>\n'
-        '    <meta content="-1" name="dtb:totalPageCount"/>\n'
-        '    <meta content="-1" name="dtb:maxPageNumber"/>\n'
-        '  </head>\n'
-        '  <docTitle>\n'
-        '    <text>' + state.book.title.strip() + '</text>\n'
-        '  </docTitle>\n'
-        '  <navMap>\n'
-        '    <navPoint id="cover" playOrder="1">\n'
-        '      <navLabel>\n'
-        '        <text>Cover</text>\n'
-        '      </navLabel>\n'
-        '      <content src="Text/cover.xhtml"/>\n'
-        '    </navPoint>\n'
-    )
-    contentsend = "  </navMap>\n</ncx>"
-
     number = 2
-    for section in state.book.sections:
+    for section in ctx.book.sections:
         if section.type != "toc":
             navpoints.append(
                 '\t<navPoint id ="' + section.name.strip() + '" playOrder="' + str(number) + '">\n'
-                '\t\t<navLabel>\n\t\t\t<text>' + section.title.strip() + '</text>\n\t\t</navLabel>\n'
+                "\t\t<navLabel>\n\t\t\t<text>" + section.title.strip() + "</text>\n\t\t</navLabel>\n"
                 '\t\t<content src="Text/' + section.name.strip() + '.xhtml"/>\n\t</navPoint>\n'
             )
             number += 1
 
-    contents = contentsstart + "".join(navpoints) + contentsend
+    contents = (
+        '<?xml version="1.0" encoding="UTF-8" standalone="no" ?>\n'
+        '<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN" "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">\n'
+        '<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1">\n'
+        "  <head>\n"
+        '    <meta content="urn:isbn:' + str(ctx.book.uuid) + '" name="dtb:uid"/>\n'
+        '    <meta content="1" name="dtb:depth"/>\n'
+        '    <meta content="-1" name="dtb:totalPageCount"/>\n'
+        '    <meta content="-1" name="dtb:maxPageNumber"/>\n'
+        "  </head>\n"
+        "  <docTitle>\n"
+        "    <text>" + ctx.book.title.strip() + "</text>\n"
+        "  </docTitle>\n"
+        "  <navMap>\n"
+        '    <navPoint id="cover" playOrder="1">\n'
+        "      <navLabel>\n"
+        "        <text>Cover</text>\n"
+        "      </navLabel>\n"
+        '      <content src="Text/cover.xhtml"/>\n'
+        "    </navPoint>\n"
+        + "".join(navpoints)
+        + "  </navMap>\n</ncx>"
+    )
 
-    ncx = open(file, access)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.ncx"), "w") as f:
-    ncx.write(contents)
+        f.write(contents)
-    ncx.close()
+
-    if state.verbose:
+    if ctx.verbose:
         print("Finished writing ncx")
 
 
-def writeTOC(section):
+def write_toc(ctx: BuildContext, section) -> None:
-    access = 'w'
-    file = os.path.join(state.book.directory, 'OEBPS', 'toc.xhtml')
     contents = (
         '<?xml version="1.0" encoding="utf-8"?>\n'
         '<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">\n'
-        '  <head>\n'
+        "  <head>\n"
-        '  <title>Table of Contents</title>\n'
+        "  <title>Table of Contents</title>\n"
         '  <link href="Styles/style.css" rel="stylesheet" type="text/css" />\n'
-        '</head>\n'
+        "</head>\n"
-        '<body>\n'
+        "<body>\n"
+        + section.body
+        + "\n</body>\n</html>"
     )
-    contents += section.body
+
-    contents += '\n</body>\n</html>'
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.xhtml"), "w") as f:
-    toc = open(file, access)
+        f.write(contents)
-    toc.write(contents)
+
-    toc.close()
+    if ctx.verbose:
-    if state.verbose:
         print("Finished writing toc")
 
 
-def writeCover():
+def write_cover(ctx: BuildContext) -> None:
-    access = 'w'
-    file = os.path.join(state.book.directory, 'OEBPS', 'Text', 'cover.xhtml')
     contents = (
         '<?xml version="1.0" encoding="utf-8" standalone="no"?>\n'
         '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"\n'
         '"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n\n'
         '<html xmlns="http://www.w3.org/1999/xhtml">\n'
-        '  <head>\n'
+        "  <head>\n"
-        '    <title>Cover</title>\n'
+        "    <title>Cover</title>\n"
         '    <style type="text/css">\n'
-        '      /*  <![CDATA[  */\n'
+        "      /*  <![CDATA[  */\n"
-        '      img { max-width: 100%; }\n'
+        "      img { max-width: 100%; }\n"
-        '      body { oeb-column-number: 1; }\n'
+        "      body { oeb-column-number: 1; }\n"
-        '      #cover-image { text-align: center; }\n'
+        "      #cover-image { text-align: center; }\n"
-        '      /*  ]]>  */\n'
+        "      /*  ]]>  */\n"
-        '    </style>\n'
+        "    </style>\n"
-        '  </head>\n'
+        "  </head>\n"
-        '  <body>\n'
+        "  <body>\n"
         '    <div id="cover-image">\n'
-        '      <img alt="' + state.book.title.strip() + '" src="../Images/cover.jpeg" />\n'
+        '      <img alt="' + ctx.book.title.strip() + '" src="../Images/cover.jpeg" />\n'
-        '    </div>\n'
+        "    </div>\n"
-        '  </body>\n'
+        "  </body>\n"
-        '</html>\n'
+        "</html>\n"
     )
-    cover = open(file, access)
-    cover.write(contents)
-    cover.close()
 
-    new = os.path.join(state.book.directory, "OEBPS", "Images", "cover.jpeg")
+    with open(os.path.join(ctx.book.directory, "OEBPS", "Text", "cover.xhtml"), "w") as f:
-    old = os.path.join(os.path.split(state.book.filename)[0], "Images", "cover.jpeg")
+        f.write(contents)
-    copy(old, new)
+
-    if state.verbose:
+    source_dir = os.path.split(ctx.book.filename)[0]
+    copy(
+        os.path.join(source_dir, "Images", "cover.jpeg"),
+        os.path.join(ctx.book.directory, "OEBPS", "Images", "cover.jpeg"),
+    )
+
+    if ctx.verbose:
         print("Finished writing cover")
 
 
-def writeContents():
+def write_contents(ctx: BuildContext) -> None:
     contents = '<?xml version="1.0" encoding="UTF-8"?>\n'
     contents += '<package xmlns="http://www.idpf.org/2007/opf" version="3.0" xml:lang="en" unique-identifier="bookid" prefix="rendition: http://www.idpf.org/vocab/rendition/# cc: http://creativecommons.org/ns#">\n'
     contents += '  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">\n'
-    contents += '    <dc:identifier id="bookid">urn:uuid' + state.book.isbn + '</dc:identifier>\n'
+    contents += '    <dc:identifier id="bookid">urn:uuid' + ctx.book.isbn + "</dc:identifier>\n"
-    contents += '    <dc:title id="pub-title">' + state.book.title.strip() + '</dc:title>\n'
+    contents += '    <dc:title id="pub-title">' + ctx.book.title.strip() + "</dc:title>\n"
     contents += '    <meta refines="#pub-title" property="title-type">main</meta>\n'
-    if state.book.titlesort != "":
+    if ctx.book.titlesort:
-        contents += '    <meta refines="#pub-title" property="file-as">' + state.book.titlesort + '</meta>\n'
+        contents += '    <meta refines="#pub-title" property="file-as">' + ctx.book.titlesort + "</meta>\n"
-    if state.book.series.name != "":
+    if ctx.book.series.name:
         print("found a book series")
-        contents += '    <dc:title id="pub-title2">' + state.book.series.name.strip() + '</dc:title>\n'
+        contents += '    <dc:title id="pub-title2">' + ctx.book.series.name.strip() + "</dc:title>\n"
         contents += '    <meta refines="#pub-title2" property="title-type">collection</meta>\n'
-        contents += '    <dc:title id="pub-title3">' + state.book.series.number + '</dc:title>\n'
+        contents += '    <dc:title id="pub-title3">' + ctx.book.series.number + "</dc:title>\n"
         contents += '    <meta refines="#pub-title3" property="title-type">display-seq</meta>\n'
-        contents += '    <meta name="calibre:series" content="' + state.book.series.name.strip() + '" />\n'
+        contents += '    <meta name="calibre:series" content="' + ctx.book.series.name.strip() + '" />\n'
-        contents += '    <meta name="calibre:series_index" content="' + state.book.series.number.strip() + '" />\n'
+        contents += '    <meta name="calibre:series_index" content="' + ctx.book.series.number.strip() + '" />\n'
     contents += '    <dc:language id="pub-language">en</dc:language>\n'
-    contents += '    <dc:date>' + state.book.publishDate + '</dc:date>\n'
+    contents += "    <dc:date>" + ctx.book.publish_date + "</dc:date>\n"
-    for name in state.book.author:
+    for name in ctx.book.author:
-        contents += '    <dc:creator id="author">' + name.first.strip() + ' ' + name.last.strip() + '</dc:creator>\n'
+        contents += '    <dc:creator id="author">' + name.first.strip() + " " + name.last.strip() + "</dc:creator>\n"
     contents += '    <meta refines="#author" scheme="marc:relators" property="role">aut</meta>\n'
-    for name in state.book.author:
+    for name in ctx.book.author:
-        contents += '    <meta refines="#author" property="file-as">' + name.last.strip() + ', ' + name.first.strip() + '</meta>\n'
+        contents += '    <meta refines="#author" property="file-as">' + name.last.strip() + ", " + name.first.strip() + "</meta>\n"
-    contents += '    <dc:publisher>' + state.book.publisher.strip() + '</dc:publisher>\n'
+    contents += "    <dc:publisher>" + ctx.book.publisher.strip() + "</dc:publisher>\n"
-    contents += '    <dc:rights>' + state.book.copyright.strip() + '</dc:rights>\n'
+    contents += "    <dc:rights>" + ctx.book.copyright.strip() + "</dc:rights>\n"
-    contents += '    <dc:subject>' + state.book.subjects.strip() + '</dc:subject>\n'
+    contents += "    <dc:subject>" + ctx.book.subjects.strip() + "</dc:subject>\n"
-    contents += '    <dc:source>' + state.book.source.strip() + '</dc:source>\n'
+    contents += "    <dc:source>" + ctx.book.source.strip() + "</dc:source>\n"
     contents += '    <meta name="cover" content="cover.jpeg" />\n'
-    contents += '  </metadata>\n'
+    contents += "  </metadata>\n"
-    contents += '  <manifest>\n'
+    contents += "  <manifest>\n"
     contents += '    <item href="Images/cover.jpeg" id="cover.jpeg" media-type="image/jpeg" properties="cover-image" />\n'
     contents += '    <item href="Text/cover.xhtml" id="cover" media-type="application/xhtml+xml" />\n'
     contents += '    <item href="toc.xhtml" id="toc" media-type="application/xhtml+xml" properties="nav"/>\n'
@@ -206,107 +206,106 @@ def writeContents():
     contents += '    <item href="Styles/invisible1.ttf" id="invisible1" media-type="application/vnd.ms-opentype" />\n'
     contents += '    <item href="Styles/Inconsolata-Regular.otf" id="inconsolate" media-type="application/vnd.ms-opentype" />\n'
 
-    if len(state.book.images) > 0:
+    if ctx.book.images:
         contents += '    <item href="Text/illustrations.xhtml" id="illustrations" media-type="application/xhtml+xml" />\n'
 
-    for section in state.book.sections:
+    for section in ctx.book.sections:
-        if section.type != 'toc':
+        if section.type != "toc":
             contents += '    <item href="Text/' + section.name + '.xhtml" id="' + section.name + '" media-type="application/xhtml+xml" />\n'
 
-    for image in state.book.images:
+    source_dir = os.path.split(ctx.book.filename)[0]
-        contents += '    <item href="Images/' + image.name + '" id="' + image.name.split('.')[0] + '" media-type="image/' + image.type + '" />\n'
+    for image in ctx.book.images:
-        new = os.path.join(state.book.directory, "OEBPS", "Images", image.name)
+        contents += '    <item href="Images/' + image.name + '" id="' + image.name.split(".")[0] + '" media-type="image/' + image.type + '" />\n'
-        old = os.path.join(os.path.split(state.book.filename)[0], "Images", image.name)
+        copy(
-        copy(old, new)
+            os.path.join(source_dir, "Images", image.name),
+            os.path.join(ctx.book.directory, "OEBPS", "Images", image.name),
+        )
 
-    contents += '  </manifest>\n'
+    contents += "  </manifest>\n"
     contents += '  <spine toc="ncx">\n'
     contents += '    <itemref idref="cover" />\n'
-    if len(state.book.images) > 0:
+    if ctx.book.images:
         contents += '    <itemref idref="illustrations" />\n'
-    for section in state.book.sections:
+    for section in ctx.book.sections:
         contents += '    <itemref idref="' + section.name + '" />\n'
-    contents += '  </spine>\n'
+    contents += "  </spine>\n"
-    contents += '  <guide>\n'
+    contents += "  <guide>\n"
     contents += '    <reference href="Text/cover.xhtml" title="Cover" type="cover" />\n'
     contents += '    <reference href="toc.xhtml" title="Table of Contents" type="toc" />\n'
-    if len(state.book.images) > 0:
+    if ctx.book.images:
         contents += '    <reference href="Text/illustrations.xhtml" title="Illustrations" type="text" />\n'
-    for section in state.book.sections:
+    for section in ctx.book.sections:
-        if section.type != 'toc':
+        if section.type != "toc":
             contents += '    <reference href="Text/' + section.name.strip() + '.xhtml" title="' + section.title.strip() + '" type="' + section.type.strip() + '" />\n'
-    contents += '  </guide>\n'
+    contents += "  </guide>\n"
-    contents += '</package>\n'
+    contents += "</package>\n"
 
-    access = 'w'
+    with open(os.path.join(ctx.book.directory, "OEBPS", "content.opf"), "w") as f:
-    file = os.path.join(state.book.directory, 'OEBPS', 'content.opf')
+        f.write(contents)
-    content = open(file, access)
+
-    content.write(contents)
+    if ctx.verbose:
-    content.close()
-    if state.verbose:
         print("Finished writing content")
 
 
-def writeSections():
+def write_sections(ctx: BuildContext) -> None:
-    access = 'w'
+    for section in ctx.book.sections:
-    for section in state.book.sections:
         if section.type.strip() == "toc":
-            writeTOC(section)
+            write_toc(ctx, section)
             continue
         contents = (
             '<?xml version="1.0" encoding="utf-8" standalone="no"?>\n'
             '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"\n'
             '"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n\n'
             '<html  xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">\n'
-            '  <head>\n'
+            "  <head>\n"
-            '    <title>' + section.title.strip() + '</title>\n'
+            "    <title>" + section.title.strip() + "</title>\n"
             '    <link href="../Styles/style.css" rel="stylesheet" type="text/css" />\n'
-            '  </head>\n'
+            "  </head>\n"
-            '  <body>\n'
+            "  <body>\n"
             '    <div id="' + section.name.strip() + '" xml:lang="en-US">\n'
+            + section.body
+            + "    </div>\n  </body>\n</html>\n"
         )
-        contents += section.body
+        with open(os.path.join(ctx.book.directory, "OEBPS", "Text", section.name.strip() + ".xhtml"), "w") as f:
-        contents += "    </div>\n  </body>\n</html>\n"
+            f.write(contents)
-        file = os.path.join(state.book.directory, 'OEBPS', 'Text', section.name.strip() + ".xhtml")
+        if ctx.verbose:
-        content = open(file, access)
-        content.write(contents)
-        content.close()
-        if state.verbose:
             print(f"Finished writing section {section.name}.xhtml")
 
 
-def writeIllustrations():
+def write_illustrations(ctx: BuildContext) -> None:
-    if len(state.book.images) == 0:
+    if not ctx.book.images:
         return
 
-    access = 'w'
     contents = (
         '<?xml version="1.0" encoding="utf-8" standalone="no"?>\n'
         '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"\n'
         '"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n\n'
         '<html  xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">\n'
-        '<head>\n'
+        "<head>\n"
-        '<title>Illustrations</title>\n'
+        "<title>Illustrations</title>\n"
         '<link href="../Styles/style.css" rel="stylesheet" type="text/css" />\n'
-        '</head>\n'
+        "</head>\n"
-        '<body>\n'
+        "<body>\n"
         '  <h1 class="title">Illustrations</h1>\n'
-        '  <table>\n'
+        "  <table>\n"
     )
-    for image in state.book.images:
+    for image in ctx.book.images:
-        contents += '    <tr><td><a href="../Images/' + image.name + '">' + image.caption + '</a></td></tr>\n'
+        contents += '    <tr><td><a href="../Images/' + image.name + '">' + image.caption + "</a></td></tr>\n"
-    contents += '  </table>\n</body>\n</html>'
+    contents += "  </table>\n</body>\n</html>"
 
-    file = os.path.join(state.book.directory, 'OEBPS', 'Text', "illustrations.xhtml")
+    with open(os.path.join(ctx.book.directory, "OEBPS", "Text", "illustrations.xhtml"), "w") as f:
-    content = open(file, access)
+        f.write(contents)
-    content.write(contents)
+
-    content.close()
+    if ctx.verbose:
-    if state.verbose:
         print("Finished writing section illustrations.xhtml")
 
 
-def writeEpub():
+def write_epub(ctx: BuildContext) -> None:
-    cmd = f'cd {state.book.directory}; zip -X0 "{state.book.directory}.epub" mimetype; zip -X9Dr "{state.book.directory}.epub" META-INF OEBPS'
+    cmd = (
+        f'cd {ctx.book.directory}; '
+        f'zip -X0 "{ctx.book.directory}.epub" mimetype; '
+        f'zip -X9Dr "{ctx.book.directory}.epub" META-INF OEBPS'
+    )
     subprocess.run(cmd, shell=True)
-    if state.verbose:
+    if ctx.verbose:
-        print(f"Finished writing {state.book.directory}.epub")
+        print(f"Finished writing {ctx.book.directory}.epub")

tests/test_models.py

@@ -0,0 +1,71 @@
+from epubmaker.models import Name, Series, Image, Section, Book, BuildContext
+
+
+def test_name_defaults():
+    n = Name()
+    assert n.first == ""
+    assert n.last == ""
+
+
+def test_series_defaults():
+    s = Series()
+    assert s.number == ""
+    assert s.name == ""
+
+
+def test_image_defaults():
+    img = Image()
+    assert img.name == ""
+    assert img.type == ""
+    assert img.alt == ""
+    assert img.caption == ""
+
+
+def test_section_defaults():
+    s = Section()
+    assert s.type == ""
+    assert s.name == ""
+    assert s.title == ""
+    assert s.body == ""
+
+
+def test_book_defaults():
+    b = Book()
+    assert b.filename == ""
+    assert b.title == ""
+    assert b.titlesort == ""
+    assert b.publisher == ""
+    assert b.isbn == ""
+    assert b.uuid == ""
+    assert b.author == []
+    assert b.images == []
+    assert b.sections == []
+
+
+def test_book_nested_objects():
+    b = Book()
+    assert isinstance(b.series, Series)
+    assert isinstance(b.artist, Name)
+    assert isinstance(b.editor, Name)
+    assert isinstance(b.cover, Image)
+
+
+def test_book_author_lists_are_independent():
+    b1 = Book()
+    b2 = Book()
+    b1.author.append(Name(first="Jane", last="Doe"))
+    assert len(b2.author) == 0
+
+
+def test_build_context_defaults():
+    ctx = BuildContext()
+    assert isinstance(ctx.book, Book)
+    assert ctx.verbose is False
+    assert ctx.in_section is False
+
+
+def test_build_context_books_are_independent():
+    ctx1 = BuildContext()
+    ctx2 = BuildContext()
+    ctx1.book.title = "Book One"
+    assert ctx2.book.title == ""

tests/test_parser.py

@@ -0,0 +1,249 @@
+import pytest
+from epubmaker.models import BuildContext
+from epubmaker.parser import extract, identify, parse_book
+
+
+@pytest.fixture
+def ctx():
+    return BuildContext()
+
+
+def test_extract_returns_inner_content():
+    assert extract("<!-- Title: Foo Bar -->") == "Title: Foo Bar"
+
+
+def test_extract_with_newline():
+    assert extract("<!-- Title: Foo Bar -->\n") == "Title: Foo Bar"
+
+
+def test_extract_returns_none_for_non_comment():
+    assert extract("<p>Not a comment</p>") is None
+
+
+def test_identify_directory(ctx):
+    identify("<!-- Directory: mybook -->", ctx)
+    assert ctx.book.directory == "mybook"
+    assert ctx.in_section is False
+
+
+def test_identify_title_plain(ctx):
+    identify("<!-- Title: My Book -->", ctx)
+    assert ctx.book.title == "My Book"
+    assert ctx.book.titlesort == ""
+
+
+def test_identify_title_the(ctx):
+    identify("<!-- Title: The Great Book -->", ctx)
+    assert ctx.book.title == "The Great Book"
+    assert ctx.book.titlesort == "Great Book, The"
+
+
+def test_identify_title_a(ctx):
+    identify("<!-- Title: A Good Story -->", ctx)
+    assert ctx.book.title == "A Good Story"
+    assert ctx.book.titlesort == "Good Story, A"
+
+
+def test_identify_title_an(ctx):
+    identify("<!-- Title: An Old Tale -->", ctx)
+    assert ctx.book.title == "An Old Tale"
+    assert ctx.book.titlesort == "Old Tale, An"
+
+
+def test_identify_author(ctx):
+    identify("<!-- Author: Smith, John -->", ctx)
+    assert len(ctx.book.author) == 1
+    assert ctx.book.author[0].last == "Smith"
+    assert ctx.book.author[0].first == "John"
+
+
+def test_identify_multiple_authors(ctx):
+    identify("<!-- Author: Smith, John -->", ctx)
+    identify("<!-- Author: Jones, Jane -->", ctx)
+    assert len(ctx.book.author) == 2
+    assert ctx.book.author[1].last == "Jones"
+
+
+def test_identify_editor(ctx):
+    identify("<!-- Editor: Brown, Alice -->", ctx)
+    assert ctx.book.editor.last == "Brown"
+    assert ctx.book.editor.first == "Alice"
+
+
+def test_identify_publisher(ctx):
+    identify("<!-- Publisher: Acme Press -->", ctx)
+    assert ctx.book.publisher == "Acme Press"
+
+
+def test_identify_copyright(ctx):
+    identify("<!-- Copyright: 2024 Author -->", ctx)
+    assert ctx.book.copyright == "2024 Author"
+
+
+def test_identify_isbn(ctx):
+    identify("<!-- ISBN: 978-0-000-00000-0 -->", ctx)
+    assert ctx.book.isbn == "978-0-000-00000-0"
+
+
+def test_identify_uuid_explicit(ctx):
+    identify("<!-- UUID: abc-123 -->", ctx)
+    assert ctx.book.uuid == "abc-123"
+
+
+def test_identify_uuid_empty_generates_uuid(ctx):
+    identify("<!-- UUID:  -->", ctx)
+    assert ctx.book.uuid != ""
+    assert ctx.book.uuid is not None
+
+
+def test_identify_source(ctx):
+    identify("<!-- Source: Some Original Work -->", ctx)
+    assert ctx.book.source == "Some Original Work"
+
+
+def test_identify_subjects(ctx):
+    identify("<!-- Subjects: Fiction, Mystery -->", ctx)
+    assert ctx.book.subjects == "Fiction, Mystery"
+
+
+def test_identify_series(ctx):
+    identify("<!-- Series: 1 My Series Name -->", ctx)
+    assert ctx.book.series.number == "1"
+    assert ctx.book.series.name == "My Series Name"
+
+
+def test_identify_cover(ctx):
+    identify("<!-- Cover: cover.jpeg -->", ctx)
+    assert ctx.book.cover.name == "cover"
+    assert ctx.book.cover.type == "jpeg"
+
+
+def test_identify_text_section(ctx):
+    identify("<!-- Text: chapter1 Chapter One -->", ctx)
+    assert ctx.in_section is True
+    assert len(ctx.book.sections) == 1
+    assert ctx.book.sections[0].type == "text"
+    assert ctx.book.sections[0].name == "chapter1"
+    assert ctx.book.sections[0].title == "Chapter One"
+
+
+def test_identify_toc_section(ctx):
+    identify("<!-- TOC: toc Table of Contents -->", ctx)
+    assert ctx.in_section is True
+    assert ctx.book.sections[0].type == "toc"
+
+
+def test_identify_title_page(ctx):
+    identify("<!-- TitlePage: tp Title Page -->", ctx)
+    assert ctx.book.sections[0].type == "title"
+
+
+def test_identify_copyright_page(ctx):
+    identify("<!-- CopyrightPage: cp Copyright -->", ctx)
+    assert ctx.book.sections[0].type == "copyright-page"
+
+
+def test_identify_dedication(ctx):
+    identify("<!-- Dedication: ded For someone -->", ctx)
+    assert ctx.book.sections[0].type == "dedication"
+
+
+def test_identify_foreward(ctx):
+    identify("<!-- Foreward: fw Foreword -->", ctx)
+    assert ctx.book.sections[0].type == "forward"
+
+
+def test_identify_notes(ctx):
+    identify("<!-- Notes: notes Notes -->", ctx)
+    assert ctx.book.sections[0].type == "notes"
+
+
+def test_identify_acknowledgement(ctx):
+    identify("<!-- Acknowledgement: ack Acknowledgements -->", ctx)
+    assert ctx.book.sections[0].type == "acknowledgement"
+
+
+def test_identify_metadata_clears_in_section(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    assert ctx.in_section is True
+    identify("<!-- Title: My Book -->", ctx)
+    assert ctx.in_section is False
+
+
+def test_identify_image_jpeg(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    identify("<!-- Image: photo.jpg Alt text::Caption text -->", ctx)
+    assert len(ctx.book.images) == 1
+    assert ctx.book.images[0].name == "photo.jpg"
+    assert ctx.book.images[0].type == "jpeg"
+    assert ctx.book.images[0].alt == "Alt text"
+    assert ctx.book.images[0].caption == "Caption text"
+
+
+def test_identify_image_png(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    identify("<!-- Image: photo.png Alt text::Caption -->", ctx)
+    assert ctx.book.images[0].type == "png"
+
+
+def test_identify_image_appends_to_section_body(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    identify("<!-- Image: photo.jpg Alt::Caption -->", ctx)
+    assert "photo.jpg" in ctx.book.sections[-1].body
+
+
+def test_identify_image_with_caption_uses_div(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    identify("<!-- Image: photo.jpg Alt::My Caption -->", ctx)
+    assert '<div class="center group">' in ctx.book.sections[-1].body
+    assert "My Caption" in ctx.book.sections[-1].body
+
+
+def test_identify_image_without_caption_uses_img(ctx):
+    identify("<!-- Text: ch1 Chapter One -->", ctx)
+    identify("<!-- Image: photo.jpg Alt:: -->", ctx)
+    body = ctx.book.sections[-1].body
+    assert "<img" in body
+    assert '<div class="center group">' not in body
+
+
+def test_identify_unknown_key_ignored(ctx):
+    identify("<!-- UnknownKey: some value -->", ctx)
+    assert ctx.book.title == ""
+    assert ctx.book.directory == ""
+
+
+def test_parse_book_populates_book(tmp_path):
+    source = tmp_path / "book.html"
+    source.write_text(
+        "<!-- Directory: mybook -->\n"
+        "<!-- Title: Test Book -->\n"
+        "<!-- Author: Doe, Jane -->\n"
+        "<!-- Text: ch1 Chapter One -->\n"
+        "<p>Body content</p>\n"
+    )
+    ctx = BuildContext()
+    ctx.book.filename = str(source)
+    parse_book(ctx)
+    assert ctx.book.title == "Test Book"
+    assert ctx.book.directory == "mybook"
+    assert len(ctx.book.author) == 1
+    assert ctx.book.author[0].last == "Doe"
+    assert len(ctx.book.sections) == 1
+    assert "<p>Body content</p>\n" in ctx.book.sections[0].body
+
+
+def test_parse_book_body_not_captured_outside_section(tmp_path):
+    source = tmp_path / "book.html"
+    source.write_text(
+        "<!-- Title: Test Book -->\n"
+        "<p>This is outside any section</p>\n"
+        "<!-- Text: ch1 Chapter One -->\n"
+        "<p>Inside section</p>\n"
+    )
+    ctx = BuildContext()
+    ctx.book.filename = str(source)
+    parse_book(ctx)
+    assert len(ctx.book.sections) == 1
+    assert "outside any section" not in ctx.book.sections[0].body
+    assert "Inside section" in ctx.book.sections[0].body

tests/test_writer.py

@@ -0,0 +1,243 @@
+import os
+import pytest
+from unittest.mock import patch
+from epubmaker.models import BuildContext, Book, Section, Image, Name
+
+
+@pytest.fixture
+def ctx(tmp_path):
+    context = BuildContext()
+    context.book.title = "Test Book"
+    context.book.uuid = "test-uuid-1234"
+    context.book.isbn = "978-0-000-00000-0"
+    context.book.publisher = "Test Publisher"
+    context.book.copyright = "2024 Test"
+    context.book.subjects = "Fiction"
+    context.book.source = "Original Source"
+    context.book.publish_date = "2024-1-1"
+    context.book.directory = str(tmp_path / "testbook")
+    context.book.filename = str(tmp_path / "source" / "book.html")
+    context.book.author.append(Name(first="Jane", last="Doe"))
+    return context
+
+
+from epubmaker.writer import (
+    write_structure, write_misc, write_ncx, write_toc,
+    write_cover, write_contents, write_sections, write_illustrations,
+)
+
+
+# --- write_structure ---
+
+def test_write_structure_creates_epub_directories(ctx):
+    write_structure(ctx, overwrite=False)
+    for subdir in ["META-INF", "OEBPS", "OEBPS/Images", "OEBPS/Styles", "OEBPS/Text"]:
+        assert os.path.isdir(os.path.join(ctx.book.directory, subdir))
+
+
+def test_write_structure_exits_if_exists(ctx):
+    os.makedirs(ctx.book.directory)
+    with pytest.raises(SystemExit):
+        write_structure(ctx, overwrite=False)
+
+
+def test_write_structure_overwrite_replaces_existing(ctx):
+    os.makedirs(ctx.book.directory)
+    sentinel = os.path.join(ctx.book.directory, "old_file.txt")
+    open(sentinel, "w").close()
+    write_structure(ctx, overwrite=True)
+    assert os.path.isdir(ctx.book.directory)
+    assert not os.path.exists(sentinel)
+
+
+# --- write_misc ---
+
+def test_write_misc_mimetype_content(ctx):
+    write_structure(ctx, overwrite=False)
+    write_misc(ctx)
+    with open(os.path.join(ctx.book.directory, "mimetype")) as f:
+        assert f.read() == "application/epub+zip"
+
+
+def test_write_misc_container_xml_references_opf(ctx):
+    write_structure(ctx, overwrite=False)
+    write_misc(ctx)
+    with open(os.path.join(ctx.book.directory, "META-INF", "container.xml")) as f:
+        assert 'full-path="OEBPS/content.opf"' in f.read()
+
+
+def test_write_misc_ibooks_display_options_created(ctx):
+    write_structure(ctx, overwrite=False)
+    write_misc(ctx)
+    path = os.path.join(ctx.book.directory, "META-INF", "com.apple.ibooks.display-options.xml")
+    assert os.path.isfile(path)
+
+
+# --- write_ncx ---
+
+def test_write_ncx_contains_title_and_uuid(ctx):
+    write_structure(ctx, overwrite=False)
+    write_ncx(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.ncx")) as f:
+        content = f.read()
+    assert ctx.book.title in content
+    assert ctx.book.uuid in content
+
+
+def test_write_ncx_includes_non_toc_sections(ctx):
+    ctx.book.sections.append(Section(type="text", name="chapter1", title="Chapter One"))
+    write_structure(ctx, overwrite=False)
+    write_ncx(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.ncx")) as f:
+        content = f.read()
+    assert "chapter1" in content
+    assert "Chapter One" in content
+
+
+def test_write_ncx_excludes_toc_type_sections(ctx):
+    ctx.book.sections.append(Section(type="toc", name="toc", title="Table of Contents"))
+    write_structure(ctx, overwrite=False)
+    write_ncx(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.ncx")) as f:
+        content = f.read()
+    assert 'id ="toc"' not in content
+
+
+def test_write_ncx_play_order_increments(ctx):
+    for i in range(3):
+        ctx.book.sections.append(Section(type="text", name=f"ch{i}", title=f"Chapter {i}"))
+    write_structure(ctx, overwrite=False)
+    write_ncx(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.ncx")) as f:
+        content = f.read()
+    assert 'playOrder="2"' in content
+    assert 'playOrder="3"' in content
+    assert 'playOrder="4"' in content
+
+
+# --- write_toc ---
+
+def test_write_toc_writes_section_body(ctx):
+    section = Section(body="<p>Contents here</p>\n")
+    write_structure(ctx, overwrite=False)
+    write_toc(ctx, section)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "toc.xhtml")) as f:
+        content = f.read()
+    assert "<p>Contents here</p>" in content
+    assert "Table of Contents" in content
+
+
+# --- write_cover ---
+
+def test_write_cover_creates_xhtml_with_title(ctx, tmp_path):
+    source_images = tmp_path / "source" / "Images"
+    source_images.mkdir(parents=True)
+    (source_images / "cover.jpeg").write_bytes(b"fake")
+    write_structure(ctx, overwrite=False)
+    write_cover(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "Text", "cover.xhtml")) as f:
+        content = f.read()
+    assert ctx.book.title in content
+    assert 'src="../Images/cover.jpeg"' in content
+
+
+def test_write_cover_copies_image_to_output(ctx, tmp_path):
+    source_images = tmp_path / "source" / "Images"
+    source_images.mkdir(parents=True)
+    (source_images / "cover.jpeg").write_bytes(b"image-data")
+    write_structure(ctx, overwrite=False)
+    write_cover(ctx)
+    assert os.path.isfile(os.path.join(ctx.book.directory, "OEBPS", "Images", "cover.jpeg"))
+
+
+# --- write_sections ---
+
+def test_write_sections_creates_xhtml_per_section(ctx):
+    ctx.book.sections.append(Section(type="text", name="chapter1", title="Chapter One", body="<p>Content</p>\n"))
+    write_structure(ctx, overwrite=False)
+    write_sections(ctx)
+    path = os.path.join(ctx.book.directory, "OEBPS", "Text", "chapter1.xhtml")
+    assert os.path.isfile(path)
+    with open(path) as f:
+        content = f.read()
+    assert "Chapter One" in content
+    assert "<p>Content</p>" in content
+
+
+def test_write_sections_routes_toc_to_toc_xhtml(ctx):
+    ctx.book.sections.append(Section(type="toc", name="toc", title="Table of Contents", body="<p>toc</p>\n"))
+    write_structure(ctx, overwrite=False)
+    write_sections(ctx)
+    assert os.path.isfile(os.path.join(ctx.book.directory, "OEBPS", "toc.xhtml"))
+    assert not os.path.isfile(os.path.join(ctx.book.directory, "OEBPS", "Text", "toc.xhtml"))
+
+
+def test_write_sections_multiple_sections(ctx):
+    for i in range(3):
+        ctx.book.sections.append(Section(type="text", name=f"ch{i}", title=f"Chapter {i}", body=f"<p>ch{i}</p>\n"))
+    write_structure(ctx, overwrite=False)
+    write_sections(ctx)
+    for i in range(3):
+        assert os.path.isfile(os.path.join(ctx.book.directory, "OEBPS", "Text", f"ch{i}.xhtml"))
+
+
+# --- write_illustrations ---
+
+def test_write_illustrations_skips_when_no_images(ctx):
+    write_structure(ctx, overwrite=False)
+    write_illustrations(ctx)
+    assert not os.path.isfile(os.path.join(ctx.book.directory, "OEBPS", "Text", "illustrations.xhtml"))
+
+
+def test_write_illustrations_creates_file_with_image_links(ctx):
+    ctx.book.images.append(Image(name="photo.jpg", caption="A scenic photo"))
+    write_structure(ctx, overwrite=False)
+    write_illustrations(ctx)
+    path = os.path.join(ctx.book.directory, "OEBPS", "Text", "illustrations.xhtml")
+    assert os.path.isfile(path)
+    with open(path) as f:
+        content = f.read()
+    assert "photo.jpg" in content
+    assert "A scenic photo" in content
+
+
+# --- write_contents ---
+
+def test_write_contents_creates_opf_with_metadata(ctx):
+    write_structure(ctx, overwrite=False)
+    write_contents(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "content.opf")) as f:
+        content = f.read()
+    assert ctx.book.title in content
+    assert ctx.book.publisher in content
+    assert ctx.book.isbn in content
+
+
+def test_write_contents_includes_section_in_manifest(ctx):
+    ctx.book.sections.append(Section(type="text", name="chapter1", title="Chapter One"))
+    write_structure(ctx, overwrite=False)
+    write_contents(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "content.opf")) as f:
+        content = f.read()
+    assert "chapter1.xhtml" in content
+
+
+def test_write_contents_includes_series_metadata(ctx):
+    ctx.book.series.name = "My Series"
+    ctx.book.series.number = "1"
+    write_structure(ctx, overwrite=False)
+    write_contents(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "content.opf")) as f:
+        content = f.read()
+    assert "My Series" in content
+    assert "calibre:series" in content
+
+
+def test_write_contents_includes_illustrations_when_images_present(ctx):
+    ctx.book.images.append(Image(name="photo.jpg", type="jpeg", caption="caption"))
+    write_structure(ctx, overwrite=False)
+    with patch("epubmaker.writer.copy"):
+        write_contents(ctx)
+    with open(os.path.join(ctx.book.directory, "OEBPS", "content.opf")) as f:
+        content = f.read()
+    assert "illustrations.xhtml" in content