From 29e0fb718a17f3eb70f40a29fa31d53e958f0006 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=96=B9=E8=80=8C=E9=9D=99?= <szdytom@163.com>
Date: Wed, 26 Oct 2022 08:50:01 +0000
Subject: [PATCH] Upload files to 'scripts'

---
 scripts/compile-lexico.html | 230 ++++++++++++++++++++++++++++++++++++
 1 file changed, 230 insertions(+)
 create mode 100644 scripts/compile-lexico.html
diff --git a/scripts/compile-lexico.html b/scripts/compile-lexico.html
new file mode 100644
index 0000000..368d27d
--- /dev/null
+++ b/scripts/compile-lexico.html
@@ -0,0 +1,230 @@
+<!DOCTYPE html>
+<html>
+<head>
+	<meta charset="utf-8">
+	<meta name="viewport" content="width=device-width, initial-scale=1">
+	<title>C'pesolino Lexici Compiler</title>
+</head>
+<body>
+
+<label for=input>lexici texto:</label><br/><textarea id=input></textarea><br/>
+<button onclick="parse()">alqa</button>
+<p id=err></p>
+
+<label for=output>markdown frutco:</label><br/>
+<textarea id=output readonly></textarea>
+
+<label for=output2>LaTeX frutco:</label><br/>
+<textarea id=output2 readonly></textarea>
+
+</body>
+
+<style type="text/css">
+	#err {
+		color:  red;
+	}
+
+	textarea {
+		width: 100%;
+		height: 300px;
+	}
+</style>
+
+<script type="text/javascript">
+
+const auxi = ['b','c','d','f','g','h','i','l','m','n','p','q','r','s','t','v','w','z','zh','dr','ts'];
+const basi = ['a','e','i','o','u','ü','ar','er','ir','or','ur','ür','ai','ei','oi','al','el','ul','ül','ao','eo','io','üo','eu','ua','au','an','en','in','on','un','ing','am','em','im','um','oen'];
+const amark = {"a": "\\\"a","b": "p","e": "e","c": "k\\super{h}","d": "t", "dd": "t", "o": "o","f": "f","u": "u","g": "g","ü": "y","h": "h","ar": "A\\textrhookschwa","i": "j","er": "7\\textrhookschwa","l": "l","ir": "i\\textrhookschwa","m": "m","or": "o\\textrhookschwa","n": "n","ur": "u\\textrhookschwa","p": "p\\super{h}","ür": "y\\textrhookschwa","q": "\\:t\\:s\\super{h}","ai": "aj","r": "\\:R\\super{w}","ei": "ej","s": "s","oi": "oj","t": "t\\super{h}","al": "6\\textltilde","v": "v","el": "eo\\textltilde","w": "w","ul": "u\\textltilde","z(1th)": "ts","ül": "4u\\textltilde","z(exa)": "z","ao": "Aw","zh": "\\:z","eo": "eo","dr": "\\t{\\:t\\:R}\\super{w}","io": "jo","ts": "ts\\super{h}","üo": "4o","eu": "ju","ua": "w\\\"a","au": "6","an": "an","en": "@n","in": "in","on": "on","un": "2n","am": "\\\"am","em": "@m","im": "im","um": "2m","ing": "iN","oen": "ow@n"};
+const bmark = {"a": "\\\"a","b": "p","e": "e","c": "k\\super{h}","i": "i","d": "t", "dd": "t", "o": "o","f": "f","u": "u","g": "g","ü": "y","h": "h","ar": "A\\textrhookschwa","er": "7\\textrhookschwa","l": "l","ir": "i\\textrhookschwa","m": "m","or": "o\\textrhookschwa","n": "n","ur": "u\\textrhookschwa","p": "p\\super{h}","ür": "y\\textrhookschwa","q": "\\:t\\:s\\super{h}","ai": "aj","r": "\\:R\\super{w}","ei": "ej","s": "s","oi": "oj","t": "t\\super{h}","al": "6\\textltilde","v": "v","el": "eo\\textltilde","w": "w","ul": "u\\textltilde","z(1th)": "ts","ül": "4u\\textltilde","z(exa)": "z","ao": "Aw","zh": "\\:z","eo": "eo","dr": "\\t{\\:t\\:R}\\super{w}","io": "jo","ts": "ts\\super{h}","üo": "4o","eu": "ju","ua": "w\\\"a","au": "6","an": "an","en": "@n","in": "in","on": "on","un": "2n","am": "\\\"am","em": "@m","im": "im","um": "2m","ing": "iN","oen": "ow@n"};
+
+
+class Lexico {
+	constructor(val, trans, pt, source) {
+		this.v = val.trim().replaceAll('ii', 'ü');
+		this.trans = trans.trim().split('/');
+		this.pt = pt.trim().split('').map(x => parseInt(x));
+		this.source = parse_source(source.trim());
+	}
+
+	get_pt() {
+		if (this.pt.length === 0) {
+			return '/';
+		}
+		let pv = this.v.replaceAll('x', 'cs').replaceAll('dd', 'd').replaceAll('\'', '');
+		if (this.pt.reduce((x, y) => x + y, 0) != pv.length) {
+			report_error('ling divo mifuto');
+			return null;
+		}
+		let res = '', c = 0, pti = 0;
+		for (let i = 0; i < pv.length; i += 1) {
+			res += pv[i];
+			c += 1;
+			if (c == this.pt[pti] && i + 1 < pv.length) {
+				c = 0;
+				res += '/';
+				pti += 1;
+			}
+		}
+		return res;
+	}
+
+	get_pt2() {
+		if (this.pt.length === 0) {
+			return [];
+		}
+		let pv = this.v.replaceAll('x', 'cs').replaceAll('dd', 'd').replaceAll('\'', '');
+		if (this.pt.reduce((x, y) => x + y, 0) != pv.length) {
+			report_error('ling divo mifuto');
+			return null;
+		}
+		let res = [], c = 0, pti = 0, cv = '';
+		for (let i = 0; i < pv.length; i += 1) {
+			cv += pv[i];
+			c += 1;
+			if (c == this.pt[pti]) {
+				c = 0;
+				res.push(cv);
+				cv = '';
+				pti += 1;
+			}
+		}
+		return res;
+	}
+
+	get_trans() {
+		return this.trans.reduce((x, y) => x + y + '；', '');
+	}
+}
+
+let LINE = 0;
+const source_types = [];
+
+function parse_source(s) {
+	// TODO: impl this
+	return s;
+}
+
+function report_error(x) {
+	document.getElementById('err').innerHTML = `focopliqo sa rovo ${LINE}: ${x}`;
+}
+
+function parse_pt_to_marco(pt) {
+	if (pt.length == 0) { return '/'; }
+
+	let res = '[';
+	for (let i = 0; i < pt.length; i += 1) {
+		let pti = pt[i];
+		let first_auxalino = '', rest = pti;
+		for (const a of auxi) {
+			if (pti.startsWith(a)) {
+				first_auxalino = a;
+				rest = pti.substring(a.length);
+				// dont break here for parsing ts, dr and zh!
+			}
+		}
+
+		if (rest.length == 0) {
+			if (first_auxalino == 'i') {
+				res += bmark['i'];
+			} else if (first_auxalino == 'z') {
+				res += amark[i == 0 ? 'z(1th)' : 'z(exa)'];
+			} else {
+				res += amark[first_auxalino];
+			}
+			continue;
+		}
+
+		let basolino = '', rauxa = '';
+		for (const b of basi) {
+			if (rest.startsWith(b)) {
+				basolino = b;
+				rauxa = rest.substring(b.length);
+				// dont break here!
+			}
+		}
+
+		if (first_auxalino == 'i' && basolino.length == 0) {
+			basolino = 'i';
+			first_auxalino = '';
+		}
+
+		if ((first_auxalino.length > 0 && basolino.length == 0) || (rauxa.length > 0 && !auxi.includes(rauxa))) {
+			report_error(`ling divo mifuto2: ${pti}`);
+			return null;
+		}
+
+		if (first_auxalino.length > 0) {
+			if (first_auxalino == 'z') {
+				res += amark[i == 0 ? 'z(1th)' : 'z(exa)'];
+			} else {
+				res += amark[first_auxalino];
+			}
+		}
+		res += '{}';
+		if (basolino.length > 0) {
+			res += bmark[basolino];
+		}
+		res += '{}';
+		if (rauxa.length > 0) {
+			if (rauxa == 'z') {
+				res += amark[rauxa + '(exa)'];
+			} else {
+				res += amark[rauxa];
+			}
+		}
+		res += '{}';
+	}
+	return res + ']';
+}
+
+function escape_tex(s) {
+	return s
+			.replaceAll('\\', '\\textbackslash{}')
+			.replaceAll('+', ' + ')
+			.replaceAll('(', ' (')
+			.replaceAll(')', ') ')
+			.replaceAll('<', '\\textless{}')
+			.replaceAll('>', '\\textgreater{}')
+			.replaceAll('#', '\\#')
+			.replaceAll('&', '\\&')
+			.replaceAll('~', '$\\sim$');
+}
+
+function parse() {
+	document.getElementById('err').innerHTML = '';
+	document.getElementById('output').value = '';
+	let t = document.getElementById('input').value.split('\n');
+	let markres = '| 单词 | 释义 | 音节划分 | 词源 |\n| :---: | :---: | :---: | :---: |\n';
+	let texres = '\\documentclass[10pt]{article}\\usepackage{tabularx}\\usepackage{ctex}\\usepackage{tipa}\\usepackage{geometry}\\geometry{a4paper,left=1cm,right=1cm,top=1.2cm,bottom=1.5cm}\\usepackage{xltabular}\\begin{document}\\newcolumntype{Y}{>{\\raggedright\\arraybackslash}X}\\centering\\begin{xltabular}{\\textwidth}{|Y|Y|l|Y|}\\hline	\\textbf{Lexici} & \\textbf{Texo} & \\textbf{Lingmarco} & \\textbf{Matro} \\\\ \\hline\n';
+	for (let i in t) {
+		LINE = parseInt(i) + 1;
+		let l = parse_item(t[i]);
+		if (l == null) {
+			return null;
+		}
+		let pt = l.get_pt();
+		if (pt == null) {
+			console.log(t[i]);
+			return null;
+		}
+		markres += `| ${l.v} | ${l.get_trans()} | ${pt} | ${l.source} |\n`;
+		texres += `\t${escape_tex(l.v)} & ${escape_tex(l.get_trans())} & \\textipa{${parse_pt_to_marco(l.get_pt2())}} & ${escape_tex(l.source)} \\\\\n\t\\hline\n`;
+	}
+	texres += `\\end{xltabular}\\end{document}`
+	document.getElementById('output').value = markres;
+	document.getElementById('output2').value = texres;
+	return true;
+}
+
+function parse_item(val) {
+	let p = val.match(/^([^\:]+):[ \t]*([^\[]+)[ \t]*\[(\d*)\;[ \t]*([^\]]*)\][ \r\n\t]*$/);
+	if (p == null) {
+		console.error(val);
+		report_error('lexo mifuto.');
+		return null;
+	}
+	return new Lexico(p[1], p[2], p[3], p[4]);
+}
+
+</script>
+</html>
\ No newline at end of file
