oldstyle-pdf-toc 0.1.0__tar.gz

oldstyle_pdf_toc-0.1.0/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.4
+Name: oldstyle-pdf-toc
+Version: 0.1.0
+Summary: Add Table of Content in scanned German old-style Textbooks
+Keywords: pdf
+Author: Hong-Phuc Bui
+Author-email: Hong-Phuc Bui <hong-phuc.bui@htwsaar.de>
+License-Expression: MIT
+Requires-Python: >=3.12
+Project-URL: Homepage, https://codeberg.org/hpb/oldstyle-pdf-toc
+Project-URL: Repository, https://codeberg.org/hpb/oldstyle-pdf-toc
+Description-Content-Type: text/markdown
+
+# Oldstyle PDF ToC
+
+## Install
+
+```shell
+pip install oldstyle-pdf-toc
+```
+
+## Usage
+
+### 1. Create the `toc.txt`
+
+The file must be nammed `toc.txt`
+
+
+```txt
+# Lines that begin with # are ignored, empty lines are alis ignored
+
+# Set page number to Uppercase roman number (I, II, III, ...)
+\pageLabel{1}{1}{UppercaseRomanNumerals}
+
+# Copy origin ToC of the book
+
+Schrifttum 11
+
+# Change page number from to decimal arabic number, reset it to 1 but physical page numer is now 13
+\pageLabel{13}{1}{DecimalArabicNumerals}
+
+# Copy other parts of the ToC of the Book
+
+I. Abbildungsverfahren 1
+1. Aufgabe der Darstellenden Geometrie 1
+2. Zentralprojektion 4
+3. Parallelprojektion 6
+
+II. Parallelprojektion und perspektive Affinität 8
+4. Invarianten der Parallelprojektion 8
+5. Der Satz von DESARGUES 11
+6. Perspektive Affinität 12
+7. Analytische Darstellung einer ebenen perspektiven Affinität 14
+8. Das Rechtwinkelpaar einer ebenen perspektiven Affinität 17
+9. Die Ellipse als affines Bild des Kreises 19
+10. Affine Eigenschaften der Ellipse 21
+11. Ellipsenkonstruktionen 23
+
+# .... others entries
+Namen- und Sachverzeichnis 339
+```
+
+The complete example `toc.txt` can be found in this project repository.
+
+### 2. Call the python script
+
+```shell
+oldstyle-pdf-toc > pdftk.toc.txt
+```
+
+### 3. Call the pdftk
+
+```shell
+pdftk Strubecker.pdf update_info_utf8 pdftk.toc.txt output Strubecker.pdf-toc.pdf
+```
+
+That's it!
+
+
+## Development
+
+This Project uses `uv` to manage dependencies and tasks during development and deployment
+
+```shell
+uv python install               # Install a copy of python to this directory
+uv venv                         # Creat a virtual python environment
+source .venv/bin/activate       # Activate venv
+uv pip install -e .             # Install this project as a python package into the virtual environment
+uv build
+```
+
+## Deploy in PyPi
+
+See: https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#create-an-account
+
+Prinzipial:
+
+```shell
+uv build
+```

oldstyle_pdf_toc-0.1.0/README.md

@@ -0,0 +1,87 @@
+# Oldstyle PDF ToC
+
+## Install
+
+```shell
+pip install oldstyle-pdf-toc
+```
+
+## Usage
+
+### 1. Create the `toc.txt`
+
+The file must be nammed `toc.txt`
+
+
+```txt
+# Lines that begin with # are ignored, empty lines are alis ignored
+
+# Set page number to Uppercase roman number (I, II, III, ...)
+\pageLabel{1}{1}{UppercaseRomanNumerals}
+
+# Copy origin ToC of the book
+
+Schrifttum 11
+
+# Change page number from to decimal arabic number, reset it to 1 but physical page numer is now 13
+\pageLabel{13}{1}{DecimalArabicNumerals}
+
+# Copy other parts of the ToC of the Book
+
+I. Abbildungsverfahren 1
+1. Aufgabe der Darstellenden Geometrie 1
+2. Zentralprojektion 4
+3. Parallelprojektion 6
+
+II. Parallelprojektion und perspektive Affinität 8
+4. Invarianten der Parallelprojektion 8
+5. Der Satz von DESARGUES 11
+6. Perspektive Affinität 12
+7. Analytische Darstellung einer ebenen perspektiven Affinität 14
+8. Das Rechtwinkelpaar einer ebenen perspektiven Affinität 17
+9. Die Ellipse als affines Bild des Kreises 19
+10. Affine Eigenschaften der Ellipse 21
+11. Ellipsenkonstruktionen 23
+
+# .... others entries
+Namen- und Sachverzeichnis 339
+```
+
+The complete example `toc.txt` can be found in this project repository.
+
+### 2. Call the python script
+
+```shell
+oldstyle-pdf-toc > pdftk.toc.txt
+```
+
+### 3. Call the pdftk
+
+```shell
+pdftk Strubecker.pdf update_info_utf8 pdftk.toc.txt output Strubecker.pdf-toc.pdf
+```
+
+That's it!
+
+
+## Development
+
+This Project uses `uv` to manage dependencies and tasks during development and deployment
+
+```shell
+uv python install               # Install a copy of python to this directory
+uv venv                         # Creat a virtual python environment
+source .venv/bin/activate       # Activate venv
+uv pip install -e .             # Install this project as a python package into the virtual environment
+uv build
+```
+
+## Deploy in PyPi
+
+See: https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#create-an-account
+
+Prinzipial:
+
+```shell
+uv build
+```

oldstyle_pdf_toc-0.1.0/pyproject.toml

@@ -0,0 +1,26 @@
+[project]
+name = "oldstyle-pdf-toc"
+version = "0.1.0"
+description = "Add Table of Content in scanned German old-style Textbooks"
+authors = [
+    {name="Hong-Phuc Bui", email="hong-phuc.bui@htwsaar.de"}
+]
+readme = "README.md"
+license = "MIT"
+keywords = ["pdf"]
+
+requires-python = ">=3.12"
+dependencies = []
+
+
+[project.urls]
+Repository = "https://codeberg.org/hpb/oldstyle-pdf-toc"
+Homepage = "https://codeberg.org/hpb/oldstyle-pdf-toc"
+
+
+[project.scripts]
+oldstyle-pdf-toc = "oldstyle_pdf_toc:main"
+
+[build-system]
+requires = ["uv_build>=0.9.21,<0.10.0"]
+build-backend = "uv_build"

oldstyle_pdf_toc-0.1.0/src/oldstyle_pdf_toc/__init__.py

@@ -0,0 +1,5 @@
+from .oldstyle_pdf_toc import *
+
+def main() -> None:
+    parse_toc_file("toc.txt")
+

oldstyle_pdf_toc-0.1.0/src/oldstyle_pdf_toc/oldstyle_pdf_toc.py

@@ -0,0 +1,188 @@
+import re
+import sys
+from dataclasses import dataclass
+
+# TODO:
+# * make page-offset for begin
+# * print pdftk command to stderr
+
+@dataclass
+class Chapter:
+    idx: str
+    """
+        Chapter Index: I, II, III, IV, ect
+    """
+
+    title: str
+    """
+        Title of the Chapter e.g. Grundlage,
+    """
+
+    page: int
+    """
+        physical page begin with 1
+    """
+
+    level: int = 1
+    """
+        ToC-Lelve 1 = chapter
+    """
+
+
+    def __str__(self):
+        idx = self.idx.strip()
+        if len(idx) > 0:
+            idx = f"{idx} "
+        return f"""BookmarkBegin
+BookmarkTitle: {idx}{self.title.strip()}
+BookmarkLevel: {self.level}
+BookmarkPageNumber: {self.page}
+"""
+
+@dataclass
+class Section(Chapter):
+    level:int = 2
+
+
+@dataclass
+class PageLabel:
+    physical_page_counter: int
+    """
+        page numer from cover to cover
+    """
+    logical_page_counter: int
+    """
+        logical page numer for each parts of the Book: Vorwort, Hauptteil, ...
+    """
+    num_style: str
+    """
+        Style from pdftk. One of "NoNumber", "LowercaseRomanNumerals", "UpercaseRomanNumerals"
+    """
+
+    def __str__(self):
+        return f"""PageLabelBegin
+PageLabelStart: {self.logical_page_counter}
+PageLabelNewIndex: {self.physical_page_counter}
+PageLabelNumStyle: {self.num_style}
+"""
+
+
+
+
+
+def parse_toc_entry(idx, line, offset) -> tuple[str,str, str]:
+    line = line.strip()
+    # chapter
+    chapter = r"""(^[IVX]+\.)(\s+)(.+[^\d$])(\d+)$"""
+    chapter_pattern = re.compile(chapter, re.MULTILINE|re.UNICODE)
+    # section
+    section = r"""(^[\d]+\.)(\s+)(.+[^\d$])(\d+)$"""
+    section_pattern = re.compile(section, re.MULTILINE|re.UNICODE)
+    # else
+    none_idx_chapter = r"(.+[^\d$])(\d+)$"
+    none_idx_chapter_pattern = re.compile(none_idx_chapter, re.MULTILINE|re.UNICODE)
+    # do the job (very ineffectiv but readable)
+    chapter_head = chapter_pattern.match(line)
+    section_head = section_pattern.match(line)
+    other_head = none_idx_chapter_pattern.match(line)
+    if chapter_head:
+        return Chapter(chapter_head[1], chapter_head[3], int(chapter_head[4]) + offset)
+    elif section_head:
+        return Section(section_head[1], section_head[3], int(section_head[4]) + offset)
+    elif other_head:
+        return Chapter("", other_head[1], int(other_head[2]) + offset)
+    else:
+        return ValueError(f">{line}< is not a ToC-entry")
+
+
+def parse_manual_info(idx, line, page_offset):
+    page_label = r"(^\\pageLabel){(\d+)}{(\d+)}{([a-z]+)}"
+    page_label_pattern = re.compile(page_label, re.IGNORECASE|re.UNICODE)
+    allowed_label_style = {"UppercaseRomanNumerals",
+                           "DecimalArabicNumerals",
+                           "LowercaseRomanNumerals",
+                           "NoNumber"}
+    match = page_label_pattern.match(line)
+    if match:
+        style = match[4]
+        if style in allowed_label_style:
+            return PageLabel(
+                int(match[2]), # physical_page_counter
+                int(match[3]), # logical_page_counter
+                style
+            )
+        else:
+            raise ValueError(f">{style}< is not allowed")
+    else:
+        raise ValueError(f">{line}< is not a pageLabel")
+
+
+def is_informative(line):
+    return len(line) > 0 and not line.startswith('#')
+
+
+def parse_toc_file(tocfilename, out=sys.stdout):
+    page_offset = 0
+    with open(tocfilename, 'r') as toc:
+        toc_line_nr = 0
+        for line in toc:
+            toc_line_nr = toc_line_nr + 1
+            line = line.strip()
+            try:
+                if is_informative(line):
+                    x = None
+                    if line.startswith( '\\' ):
+                        x = parse_manual_info(toc_line_nr, line, page_offset)
+                        page_offset = x.physical_page_counter - 1
+                    else:
+                        x = parse_toc_entry(toc_line_nr, line, page_offset)
+                    print(x, file=out, end="")
+            except ValueError as ex:
+                raise ValueError(f"{toc_line_nr} : {repr(ex)}") from ex
+
+
+if __name__ == "__main__":
+    OFFSET = 12
+    with open("toc.txt") as toc:
+        idx = 0
+        for line in toc:
+            idx = idx + 1
+            x = parse_toc_entry(idx, line, OFFSET)
+            if x:
+                print(x, end="")
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+