pantsdown 2.2.7 → 2.2.8

package/src/types.ts

@@ -52,6 +52,8 @@ export interface Tokens extends Record<string, BaseToken> {
       raw: string;
       text: string;
       tokens: Token[];
+      header: boolean;
+      align: "center" | "left" | "right" | null;
    };
    Hr: {
       type: "hr";
@@ -103,6 +105,7 @@ export interface Tokens extends Record<string, BaseToken> {
       raw: string;
       text: string;
       tokens?: Token[];
+      escaped?: boolean;
       sourceMap?: SourceMap;
    };
    Def: {
@@ -119,13 +122,18 @@ export interface Tokens extends Record<string, BaseToken> {
       text: string;
    };
    Tag: {
-      type: "text" | "html";
+      type: "html";
       raw: string;
       text: string;
       inLink: boolean;
       inRawBlock: boolean;
       block: boolean;
    };
+   Checkbox: {
+      type: "checkbox";
+      raw: string;
+      checked: boolean;
+   };
    Link: {
       type: "link";
       raw: string;
@@ -140,6 +148,7 @@ export interface Tokens extends Record<string, BaseToken> {
       text: string;
       href: string;
       title: string | null;
+      tokens: Token[];
    };
    Strong: {
       type: "strong";
@@ -222,6 +231,7 @@ export type Token =
    | Tokens["Codespan"]
    | Tokens["Br"]
    | Tokens["Del"]
+   | Tokens["Checkbox"]
    | Tokens["Alert"]
    | Tokens["Footnote"]
    | Tokens["FootnoteRef"]

package/src/utils.ts

@@ -1,13 +1,10 @@
 import { type Lexer } from "./lexer.ts";
-import { type PantsdownConfig, type HTMLAttrs, type SourceMap, type Tokens } from "./types.ts";
+import { other } from "./rules/other.ts";
+import { type HTMLAttrs, type PantsdownConfig, type SourceMap, type Tokens } from "./types.ts";
 
 /**
  * Helpers
  */
-const escapeTest = /[&<>"']/;
-const escapeReplace = new RegExp(escapeTest.source, "g");
-const escapeTestNoEncode = /[<>"']|&(?!(#\d{1,7}|#[Xx][a-fA-F0-9]{1,6}|\w+);)/;
-const escapeReplaceNoEncode = new RegExp(escapeTestNoEncode.source, "g");
 const escapeReplacements: Record<string, string> = {
    "&": "&amp;",
    "<": "&lt;",
@@ -21,12 +18,12 @@ const getEscapeReplacement = (ch: string) => escapeReplacements[ch]!;
 // https://bun.sh/docs/api/utils#bun-escapehtml
 export function escape(html: string, encode?: boolean) {
    if (encode) {
-      if (escapeTest.test(html)) {
-         return html.replace(escapeReplace, getEscapeReplacement);
+      if (other.escapeTest.test(html)) {
+         return html.replace(other.escapeReplace, getEscapeReplacement);
       }
    } else {
-      if (escapeTestNoEncode.test(html)) {
-         return html.replace(escapeReplaceNoEncode, getEscapeReplacement);
+      if (other.escapeTestNoEncode.test(html)) {
+         return html.replace(other.escapeReplaceNoEncode, getEscapeReplacement);
       }
    }
 
@@ -150,7 +147,7 @@ export function fixLocalImageHref(href: string, config: PantsdownConfig): string
 
 export function cleanUrl(href: string) {
    try {
-      href = encodeURI(href).replace(/%25/g, "%");
+      href = encodeURI(href).replace(other.percentDecode, "%");
    } catch (_) {
       return null;
    }
@@ -162,7 +159,7 @@ export const noopTest = { exec: () => null };
 export function splitCells(tableRow: string, count?: number) {
    // ensure that every cell-delimiting pipe has a space
    // before it to distinguish it from an escaped pipe
-   const row = tableRow.replace(/\|/g, (_match, offset: number, str: string) => {
+   const row = tableRow.replace(other.findPipe, (_match, offset: number, str: string) => {
          let escaped = false;
          let curr = offset;
          while (--curr >= 0 && str[curr] === "\\") escaped = !escaped;
@@ -175,7 +172,7 @@ export function splitCells(tableRow: string, count?: number) {
             return " |";
          }
       }),
-      cells = row.split(/ \|/);
+      cells = row.split(other.splitPipe);
 
    // First/last cell in a row cannot be empty if it has no leading/trailing pipe
    if (!cells[0]?.trim()) {
@@ -195,7 +192,7 @@ export function splitCells(tableRow: string, count?: number) {
 
    for (let i = 0, len = cells.length; i < len; i++) {
       // leading or trailing whitespace is ignored per the gfm spec
-      cells[i] = cells[i]!.trim().replace(/\\\|/g, "|");
+      cells[i] = cells[i]!.trim().replace(other.slashPipe, "|");
    }
    return cells;
 }
@@ -232,6 +229,20 @@ export function rtrim(str: string, c: string, invert?: boolean) {
    return str.slice(0, l - suffLen);
 }
 
+export function trimTrailingBlankLines(str: string) {
+   const lines = str.split("\n");
+   let end = lines.length - 1;
+   while (end >= 0 && other.blankLine.test(lines[end]!)) {
+      end--;
+   }
+   if (lines.length - end <= 2) {
+      // we want to keep single trailing blank lines
+      return str;
+   }
+
+   return lines.slice(0, end + 1).join("\n");
+}
+
 export function findClosingBracket(str: string, b: string) {
    if (!b[1] || !str.includes(b[1])) {
       return -1;
@@ -250,6 +261,9 @@ export function findClosingBracket(str: string, b: string) {
          }
       }
    }
+   if (level > 0) {
+      return -2;
+   }
    return -1;
 }
 
@@ -260,33 +274,24 @@ export function outputLink(
    lexer: Lexer,
 ): Tokens["Link"] | Tokens["Image"] {
    const href = link.href;
-   const title = link.title ? escape(link.title) : null;
-   const text = cap[1]?.replace(/\\([\[\]])/g, "$1") ?? "";
-
-   if (cap[0]?.charAt(0) !== "!") {
-      lexer.state.inLink = true;
-      const token: Tokens["Link"] = {
-         type: "link",
-         raw,
-         href,
-         title,
-         text,
-         tokens: lexer.inlineTokens(text),
-      };
-      lexer.state.inLink = false;
-      return token;
-   }
-   return {
-      type: "image",
+   const title = link.title || null;
+   const text = cap[1]?.replace(other.outputLinkReplace, "$1") ?? "";
+
+   lexer.state.inLink = true;
+   const token: Tokens["Link"] | Tokens["Image"] = {
+      type: cap[0]?.charAt(0) === "!" ? "image" : "link",
       raw,
       href,
       title,
-      text: escape(text),
+      text,
+      tokens: lexer.inlineTokens(text),
    };
+   lexer.state.inLink = false;
+   return token;
 }
 
 export function indentCodeCompensation(raw: string, text: string) {
-   const matchIndentToCode = /^(\s+)(?:```)/.exec(raw);
+   const matchIndentToCode = other.indentCodeCompensation.exec(raw);
 
    if (matchIndentToCode === null) {
       return text;
@@ -297,7 +302,7 @@ export function indentCodeCompensation(raw: string, text: string) {
    return text
       .split("\n")
       .map((node) => {
-         const matchIndentInNode = /^\s+/.exec(node);
+         const matchIndentInNode = other.beginningSpace.exec(node);
          if (matchIndentInNode === null) {
             return node;
          }
@@ -344,3 +349,20 @@ export const ALERTS = [
       icon: '<svg class="octicon octicon-alert" style="margin-right: 0.5rem;" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="M4.47.22A.749.749 0 0 1 5 0h6c.199 0 .389.079.53.22l4.25 4.25c.141.14.22.331.22.53v6a.749.749 0 0 1-.22.53l-4.25 4.25A.749.749 0 0 1 11 16H5a.749.749 0 0 1-.53-.22L.22 11.53A.749.749 0 0 1 0 11V5c0-.199.079-.389.22-.53Zm.84 1.28L1.5 5.31v5.38l3.81 3.81h5.38l3.81-3.81V5.31L10.69 1.5ZM8 4a.75.75 0 0 1 .75.75v3.5a.75.75 0 0 1-1.5 0v-3.5A.75.75 0 0 1 8 4Zm0 8a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"/></svg>',
    },
 ];
+
+export function expandTabs(line: string, indent = 0) {
+   let col = indent;
+   let expanded = "";
+   for (const char of line) {
+      if (char === "\t") {
+         const added = 4 - (col % 4);
+         expanded += " ".repeat(added);
+         col += added;
+      } else {
+         expanded += char;
+         col++;
+      }
+   }
+
+   return expanded;
+}