2020-06-04 06:04:57 +08:00
|
|
|
function preprocessRelations(str) {
|
|
|
|
return str.replace(/<a[^>]+href="(#root[A-Za-z0-9/]*)"[^>]*>[^<]*<\/a>/g, "$1");
|
|
|
|
}
|
|
|
|
|
2020-06-03 22:24:41 +08:00
|
|
|
function lexer(str) {
|
2020-06-04 06:04:57 +08:00
|
|
|
str = preprocessRelations(str);
|
2020-06-03 22:24:41 +08:00
|
|
|
|
|
|
|
const expressionTokens = [];
|
|
|
|
|
|
|
|
let quotes = false;
|
|
|
|
let currentWord = '';
|
|
|
|
|
|
|
|
function isOperatorSymbol(chr) {
|
|
|
|
return ['=', '*', '>', '<', '!'].includes(chr);
|
|
|
|
}
|
|
|
|
|
|
|
|
function previousOperatorSymbol() {
|
|
|
|
if (currentWord.length === 0) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
return isOperatorSymbol(currentWord[currentWord.length - 1]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
function finishWord() {
|
|
|
|
if (currentWord === '') {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2020-06-03 23:11:03 +08:00
|
|
|
expressionTokens.push(currentWord);
|
2020-06-03 22:24:41 +08:00
|
|
|
|
|
|
|
currentWord = '';
|
|
|
|
}
|
|
|
|
|
|
|
|
for (let i = 0; i < str.length; i++) {
|
|
|
|
const chr = str[i];
|
|
|
|
|
|
|
|
if (chr === '\\') {
|
|
|
|
if ((i + 1) < str.length) {
|
|
|
|
i++;
|
|
|
|
|
|
|
|
currentWord += str[i];
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
currentWord += chr;
|
|
|
|
}
|
|
|
|
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
else if (['"', "'", '`'].includes(chr)) {
|
|
|
|
if (!quotes) {
|
2020-06-03 23:11:03 +08:00
|
|
|
if (previousOperatorSymbol()) {
|
|
|
|
finishWord();
|
2020-06-03 22:24:41 +08:00
|
|
|
}
|
2020-06-03 23:11:03 +08:00
|
|
|
|
|
|
|
quotes = chr;
|
2020-06-03 22:24:41 +08:00
|
|
|
}
|
|
|
|
else if (quotes === chr) {
|
|
|
|
quotes = false;
|
|
|
|
|
|
|
|
finishWord();
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
// it's a quote but within other kind of quotes so it's valid as a literal character
|
|
|
|
currentWord += chr;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
else if (!quotes) {
|
|
|
|
if (currentWord.length === 0 && (chr === '#' || chr === '~')) {
|
|
|
|
currentWord = chr;
|
|
|
|
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
else if (chr === ' ') {
|
|
|
|
finishWord();
|
|
|
|
continue;
|
|
|
|
}
|
2020-06-03 23:11:03 +08:00
|
|
|
else if (['(', ')', '.'].includes(chr)) {
|
2020-06-03 22:24:41 +08:00
|
|
|
finishWord();
|
|
|
|
currentWord += chr;
|
|
|
|
finishWord();
|
|
|
|
continue;
|
|
|
|
}
|
2020-06-03 23:11:03 +08:00
|
|
|
else if (previousOperatorSymbol() !== isOperatorSymbol(chr)) {
|
2020-06-03 22:24:41 +08:00
|
|
|
finishWord();
|
|
|
|
|
|
|
|
currentWord += chr;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
currentWord += chr;
|
|
|
|
}
|
|
|
|
|
|
|
|
finishWord();
|
|
|
|
|
2020-06-03 23:11:03 +08:00
|
|
|
return expressionTokens;
|
2020-06-03 22:24:41 +08:00
|
|
|
}
|
|
|
|
|
2020-06-04 06:04:57 +08:00
|
|
|
function parser(tokens) {
|
|
|
|
const attrs = [];
|
|
|
|
|
|
|
|
for (let i = 0; i < tokens.length; i++) {
|
|
|
|
const token = tokens[i];
|
|
|
|
|
|
|
|
if (token.startsWith('#')) {
|
|
|
|
const attr = {
|
|
|
|
type: 'label',
|
|
|
|
name: token.substr(1)
|
|
|
|
};
|
|
|
|
|
|
|
|
if (tokens[i + 1] === "=") {
|
|
|
|
if (i + 2 >= tokens.length) {
|
|
|
|
throw new Error(`Missing value for label "${token}"`);
|
|
|
|
}
|
|
|
|
|
|
|
|
i += 2;
|
|
|
|
|
|
|
|
attr.value = tokens[i];
|
|
|
|
}
|
|
|
|
|
|
|
|
attrs.push(attr);
|
|
|
|
}
|
|
|
|
else if (token.startsWith('~')) {
|
|
|
|
const attr = {
|
|
|
|
type: 'relation',
|
|
|
|
name: token.substr(1)
|
|
|
|
};
|
|
|
|
|
|
|
|
if (i + 2 >= tokens.length || tokens[i + 1] !== '=') {
|
|
|
|
throw new Error(`Relation "${token}" should point to a note.`);
|
|
|
|
}
|
|
|
|
|
|
|
|
i += 2;
|
|
|
|
|
|
|
|
attr.value = tokens[i];
|
|
|
|
|
|
|
|
attrs.push(attr);
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
throw new Error(`Unrecognized attribute "${token}"`);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return attrs;
|
|
|
|
}
|
|
|
|
|
2020-06-03 22:24:41 +08:00
|
|
|
export default {
|
2020-06-04 06:04:57 +08:00
|
|
|
lexer,
|
|
|
|
parser
|
2020-06-03 22:24:41 +08:00
|
|
|
}
|