Initial commit

.gitignore

@@ -0,0 +1,7 @@
+data/tex
+
+# TODO: fix
+
+# tex/**/*
+# !tex/**/*.tex
+# !tex/**/*.tex

README.md

@@ -0,0 +1,21 @@
+# JLPT Nx 単語帳
+
+List of words to use when making flashcards to learn japanese.
+
+## Intended use case
+
+First of all, get some kind of flashcard solution.
+This might be a mobile app, it might be a bunch of paper slices.
+Personally, I would recommend getting a [pack of premade paper cards (image)][tangocho-link]
+
+[![Memorization cards][tangocho-img]][tangocho-link]
+
+Secondly, get one of these bad bois:
+
+![Highlighter/text marker][highlighter-img]
+
+Although not strictly required, keeping track of which of the words you've put into your memorization cards will help you avoid duplicates.
+
+[tangocho-link]: https://www.amazon.com/Copies-Books-Each-Yellow-Assortment/dp/B0012OV700/133-2864506-7558164
+[tangocho-img]: https://m.media-amazon.com/images/I/71CrpXAXmML._AC_SL1000_.jpg
+[highlighter-img]: https://static2.jetpens.com/images/a/000/178/178843.jpg?auto=format&ba=middle%2Ccenter&balph=3&blend64=aHR0cDovL3d3dy5qZXRwZW5zLmNvbS9pbWFnZXMvYXNzZXRzL3dhdGVybWFyazIucG5n&bm=difference&bs=inherit&chromasub=444&fm=jpg&h=400&mark64=aHR0cDovL3d3dy5qZXRwZW5zLmNvbS9pbWFnZXMvYXNzZXRzL3dhdGVybWFyazEucG5n&markalign=top%2Cright&markalpha=30&markscale=16&q=90&usm=20&w=600&s=78167e64fe93cce86b3e07da0f53578c

main.tex

@@ -0,0 +1,25 @@
+% !TeX program = xelatex
+\documentclass[a5paper, twoside]{article}
+
+\usepackage{xeCJK}
+\usepackage{adjustbox}
+\usepackage{graphicx}
+\usepackage{tabu}
+\usepackage{longtable}
+\usepackage{makecell}
+\usepackage[bindingoffset=0.5in]{geometry}
+
+\setCJKmainfont{Noto Sans CJK JP}
+
+\begin{document}
+  \renewcommand{\arraystretch}{2}
+    \input{tex/n5.tex}
+    \newline{}
+    \input{tex/n4.tex}
+    \newline{}
+    \input{tex/n3.tex}
+    \newline{}
+    \input{tex/n2.tex}
+    \newline{}
+    \input{tex/n1.tex}
+\end{document}

make.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+python3 ./toTex.py
+xelatex main.tex
+numberOfPages=$(pdfinfo main.pdf | awk '/^Pages:/ {print $2}')
+
+echo $numberOfPages
+
+cat >wrapper.tex <<EOF
+\\documentclass[a4paper, twoside]{article}
+\\usepackage[T1]{fontenc}
+\\usepackage[utf8]{inputenc}
+\\usepackage{pdfpages}
+\\begin{document}
+  \\includepdf[pages=-,nup=1x2,signature=${numberOfPages},landscape,booklet=true]{main.pdf}
+\\end{document}
+EOF
+
+pdflatex wrapper.tex

tex/common/frontPageNx.tex

@@ -0,0 +1,31 @@
+\usepackage{fontawesome}
+\usepackage{hyperref}
+\usepackage[
+    type={CC},
+    modifier={by},
+    version={3.0},
+]{doclicense}
+
+\newfontfamily\nscjksixty[SizeFeatures={Size=120}]{Noto Sans CJK JP}
+
+\newcommand{\NXfrontpage}[1]{
+
+  {
+    \topskip0pt
+    \vspace*{\fill}
+    \begin{center}
+      { \nscjksixty{ N#1 } } \\
+      \vspace*{5mm}
+      { \Huge 単語帳 } \\
+      \vspace*{15mm}
+      \doclicenseImage \\
+      Data made by Jonathan Waller at \url{http://www.tanos.co.uk/jlpt/jlpt#1/} \\
+      \vspace*{10mm}
+      Project at \\
+      { \Huge \faicon{github-square} } \url{https://github.com/h7x4abk3g}
+    \end{center}
+    \vspace*{\fill}
+  }
+
+  \newpage{}
+}

tex/main.tex

@@ -0,0 +1,24 @@
+% !TeX program = xelatex
+\documentclass[a5paper, twoside]{article}
+\usepackage{xeCJK}
+\usepackage{adjustbox}
+\usepackage{graphicx}
+\usepackage{tabu}
+\usepackage{longtable}
+\usepackage{makecell}
+\usepackage[bindingoffset=0.5in]{geometry}
+
+\setCJKmainfont{Noto Sans CJK JP}
+
+\begin{document}
+  \renewcommand{\arraystretch}{2}
+    \input{tex/n5.tex}
+    \newline{}
+    \input{tex/n4.tex}
+    \newline{}
+    \input{tex/n3.tex}
+    \newline{}
+    \input{tex/n2.tex}
+    \newline{}
+    \input{tex/n1.tex}
+\end{document}

tex/n1.tex

@@ -0,0 +1,20 @@
+
+% !TeX program = xelatex
+\documentclass[a5paper, twoside]{article}
+\usepackage{xeCJK}
+\usepackage{adjustbox}
+\usepackage{graphicx}
+\usepackage{tabu}
+\usepackage{longtable}
+\usepackage{makecell}
+\usepackage[bindingoffset=0.5in]{geometry}
+
+\input{common/frontPageNx.tex}
+
+\setCJKmainfont{Noto Sans CJK JP}
+
+\begin{document}
+  \renewcommand{\arraystretch}{2}
+    \NXfrontpage{1}
+    \input{../data/tex/n1.tex}
+\end{document}

toTex.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+
+from lxml import etree;
+from re import sub
+
+for n in reversed(range(1,6)):
+  with open(f'./data/html/n{n}.html', 'r') as file:
+    doc = etree.parse(file)
+
+  def extractCellText(col):
+    a = col.xpath('a')
+    if len(a) == 0: return ''
+    return sub(r'(-?\d+(?:\.\d+)?\^-?\d+(?:\.\d+)?)', r'$\1$', a[0].text.replace('#', '\\#'))
+
+  rows = (tuple(map(extractCellText, tr.xpath("td"))) for tr in doc.xpath("//tbody/tr"))
+
+  # Skip header
+  next(rows)
+
+  # Make cell with multiple rows in latex if there's multiple meanings/readings
+  def makeMultiCellIfMultipleEntries(cellText, rowtype = 'j'):
+    if rowtype == 'j' and '/' in cellText:
+      return '\\makecell[l]{ %s }' % cellText.replace('/', ' \\\\ ')
+    elif rowtype == 'e' and ',' in cellText:
+      return '\\makecell[l]{ %s }' % cellText.replace(',', ' \\\\ ')
+    else:
+      return cellText
+      
+
+  with open(f'./data/tex/n{n}.tex', 'w') as file:
+    file.write('\\begin{longtabu} to \\textwidth {ll|l}\n')
+    file.write(
+      " \\\\\\hline\n".join(f'{makeMultiCellIfMultipleEntries(row[0])} & {makeMultiCellIfMultipleEntries(row[1])} & {makeMultiCellIfMultipleEntries(row[2], rowtype="e")}' for row in rows)
+    )
+    file.write('\n\\end{longtabu}')