wip -- disambiguation works, tests passing

2026-07-05 14:09:27 -07:00
parent 9f03721f86
commit f27378dc04
3 changed files with 400 additions and 325 deletions
@@ -0,0 +1,149 @@
+function disambiguateAsteriskRuns(line: string): string {
+    const SENTINEL = '\u200C';
+    const ASTERISK_RUN = /\*{1,3}/g;
+    const stack: ('*' | '**')[] = [];
+    let result = '';
+    let lastIndex = 0;
+    let match: RegExpExecArray | null;
+
+    console.log(`DISAMBIGUATE: '${line}'`);
+
+    while ((match = ASTERISK_RUN.exec(line)) !== null) {
+
+        result += line.slice(lastIndex, match.index);
+        const run = match[0];
+
+        console.log(`DISAMBIGUATE: run == '${run}', stack == ${stack}`);
+
+        if (run.length === 3 && stack.length === 2) {
+            const innerCloser = stack.pop()!;
+            const outerCloser = stack.pop()!;
+            result += innerCloser + SENTINEL + outerCloser;
+        } else if (run.length === 3 && stack.length === 0) {
+            if (match.index == 0) {
+                result += '***';
+            } else {
+                result += '*' + SENTINEL + '**';
+                stack.push('**');
+                stack.push('*');
+            }
+        } else if (run.length === 3) {
+            result += run;
+        } else if (stack.length > 0 && stack[stack.length - 1] === run) {
+            stack.pop();
+            result += run;
+        } else {
+            stack.push(run as '*' | '**');
+            result += run;
+        }
+
+        lastIndex = match.index + run.length;
+    }
+
+    result += line.slice(lastIndex);
+    console.log(`DISAMBIGUATE: '${result}'`);
+    return result;
+}
+
+function assert(condition, message) {
+    if (!condition) { throw new Error(message); }
+}
+
+function rewrite(line: string): string {
+    const SENTINEL = '|' //'\u200C';
+    const ASTERISK_RUN = /\*{1,3}/g;
+    const stack: ('*' | '**' | '***')[] = [];
+    let result = '';
+    let lastIndex = 0;
+    let match: RegExpExecArray | null;
+
+    const bold = '**';
+    const italic = '*';
+
+    let lastSequence = '';
+
+    while ((match = ASTERISK_RUN.exec(line)) !== null) {
+        result += line.slice(lastIndex, match.index);
+        const sequence = match[0];
+
+        if (sequence.length === 3) {
+
+            // split *** into opening ** and *
+            if (stack.length === 0) {
+                result += sequence;
+                stack.push('***');
+
+            // closing ***, close the stack
+            } else if (stack.length === 1 && stack[0] === sequence) {
+                result = result.replace('***', bold + SENTINEL + italic);
+                result += italic + SENTINEL + bold;
+                stack.pop();
+
+            } else if (stack.length === 2) {
+                const inner = stack.pop();
+                const outer = stack.pop();
+                result += inner + SENTINEL + outer;
+
+            } else if (stack.length === 1) {
+                console.warn(`Cannot parsed line '${line}': invalid sequence ${sequence} with stack ${stack}!`);
+
+            } else {
+                console.warn(`UNHANDLED '${sequence}', last sequence '${lastSequence}'`);
+            }
+        } else if (stack.length) {
+            if (stack[stack.length - 1] === sequence) {
+                result += stack.pop();
+            } else if (stack.length === 1 && stack[0] === '***') {
+                const opener = stack[0].substring(0, stack[0].length - sequence.length);
+                result = result.replace('***', opener + SENTINEL + sequence);
+                result += sequence;
+                stack[0] = opener as '*' | '**';
+            } else {
+                result += sequence;
+                stack.push(sequence as '*' | '**');
+            }
+        } else {
+            stack.push(sequence as '*' | '**');
+            result += sequence;
+        }
+
+        lastIndex = match.index + sequence.length;
+    }
+
+    result += line.slice(lastIndex);
+    return result;
+}
+
+
+function test_it() {
+    console.log(rewrite('*italic **bold***'));
+    let cases = [
+        {
+            'input': '***bold-italic***',
+            'expected': '**|*bold-italic*|**'
+        },
+        {
+            'input': '***bold** italic*',
+            'expected': '*|**bold** italic*',
+        },
+        {
+            'input': '***italic* bold**',
+            'expected': '**|*italic* bold**',
+        },
+        {
+            'input': '**bold, *italic***',
+            'expected': '**bold, *italic*|**'
+        },
+        {
+            'input': '*italic, **bold***',
+            'expected': '*italic, **bold**|*'
+        },
+    ];
+
+    for (const testCase of cases) {
+        let result = rewrite(testCase.input);
+        assert(result == testCase.expected, `'${result}' (${result.length}) != '${testCase.expected}' (${testCase.expected.length})`);
+    }
+};
+
+test_it();