import {_defaults} from './defaults';
import {escape, findClosingBracket, rtrim, splitCells} from './helpers';
import type {_Lexer} from './Lexer';
import type {MarkedOptions} from './MarkedOptions';
import type {Rules} from './rules';
import type {Links, Tokens} from './Tokens';

function outputLink(cap: string[], link: Pick<Tokens.Link, 'href' | 'title'>, raw: string, 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',
        raw,
        href,
        title,
        text: escape(text),
    };
}

function indentCodeCompensation(raw: string, text: string) {
    const matchIndentToCode = raw.match(/^(\s+)(?:```)/);

    if (matchIndentToCode === null) {
        return text;
    }

    const indentToCode = matchIndentToCode[1];

    return text
        .split('\n')
        .map(node => {
            const matchIndentInNode = node.match(/^\s+/);
            if (matchIndentInNode === null) {
                return node;
            }

            const [indentInNode] = matchIndentInNode;

            if (indentInNode.length >= indentToCode.length) {
                return node.slice(indentToCode.length);
            }

            return node;
        })
        .join('\n');
}

/**
 * Tokenizer
 */
export class _Tokenizer {
    lexer!: _Lexer; // set by the lexer
    options: MarkedOptions;
    rules!: Rules; // set by the lexer

    constructor(options?: MarkedOptions) {
        this.options = options || _defaults;
    }

    autolink(src: string): Tokens.Link | undefined {
        const cap = this.rules.inline.autolink.exec(src);
        if (cap) {
            let text, href;
            if (cap[2] === '@') {
                text = escape(cap[1]);
                href = 'mailto:' + text;
            } else {
                text = escape(cap[1]);
                href = text;
            }

            return {
                type: 'link',
                raw: cap[0],
                text,
                href,
                tokens: [
                    {
                        type: 'text',
                        raw: text,
                        text,
                    },
                ],
            };
        }
    }

    blockquote(src: string): Tokens.Blockquote | undefined {
        const cap = this.rules.block.blockquote.exec(src);
        if (cap) {
            // precede setext continuation with 4 spaces so it isn't a setext
            let text = cap[0].replace(/\n {0,3}((?:=+|-+) *)(?=\n|$)/g, '\n    $1');
            text = rtrim(text.replace(/^ *>[ \t]?/gm, ''), '\n');
            const top = this.lexer.state.top;
            this.lexer.state.top = true;
            const tokens = this.lexer.blockTokens(text);
            this.lexer.state.top = top;
            return {
                type: 'blockquote',
                raw: cap[0],
                tokens,
                text,
            };
        }
    }

    br(src: string): Tokens.Br | undefined {
        const cap = this.rules.inline.br.exec(src);
        if (cap) {
            return {
                type: 'br',
                raw: cap[0],
            };
        }
    }

    code(src: string): Tokens.Code | undefined {
        const cap = this.rules.block.code.exec(src);
        if (cap) {
            const text = cap[0].replace(/^ {1,4}/gm, '');
            return {
                type: 'code',
                raw: cap[0],
                codeBlockStyle: 'indented',
                text: !this.options.pedantic
                    ? rtrim(text, '\n')
                    : text,
            };
        }
    }

    codespan(src: string): Tokens.Codespan | undefined {
        const cap = this.rules.inline.code.exec(src);
        if (cap) {
            let text = cap[2].replace(/\n/g, ' ');
            const hasNonSpaceChars = /[^ ]/.test(text);
            const hasSpaceCharsOnBothEnds = /^ /.test(text) && / $/.test(text);
            if (hasNonSpaceChars && hasSpaceCharsOnBothEnds) {
                text = text.substring(1, text.length - 1);
            }
            text = escape(text, true);
            return {
                type: 'codespan',
                raw: cap[0],
                text,
            };
        }
    }

    def(src: string): Tokens.Def | undefined {
        const cap = this.rules.block.def.exec(src);
        if (cap) {
            const tag = cap[1].toLowerCase().replace(/\s+/g, ' ');
            const href = cap[2] ? cap[2].replace(/^<(.*)>$/, '$1').replace(this.rules.inline.anyPunctuation, '$1') : '';
            const title = cap[3] ? cap[3].substring(1, cap[3].length - 1).replace(this.rules.inline.anyPunctuation,
                '$1',
            ) : cap[3];
            return {
                type: 'def',
                tag,
                raw: cap[0],
                href,
                title,
            };
        }
    }

    del(src: string): Tokens.Del | undefined {
        const cap = this.rules.inline.del.exec(src);
        if (cap) {
            return {
                type: 'del',
                raw: cap[0],
                text: cap[2],
                tokens: this.lexer.inlineTokens(cap[2]),
            };
        }
    }

    emStrong(src: string, maskedSrc: string, prevChar = ''): Tokens.Em | Tokens.Strong | undefined {
        let match = this.rules.inline.emStrongLDelim.exec(src);
        if (!match) {
            return;
        }

        // _ can't be between two alphanumerics. \p{L}\p{N} includes non-english alphabet/numbers as well
        if (match[3] && prevChar.match(/[\p{L}\p{N}]/u)) {
            return;
        }

        const nextChar = match[1] || match[2] || '';

        if (!nextChar || !prevChar || this.rules.inline.punctuation.exec(prevChar)) {
            // unicode Regex counts emoji as 1 char; spread into array for proper count (used multiple times below)
            const lLength = [...(match as any)[0]].length - 1;
            let rDelim, rLength, delimTotal = lLength, midDelimTotal = 0;

            const endReg = match[0][0] === '*'
                ? this.rules.inline.emStrongRDelimAst
                : this.rules.inline.emStrongRDelimUnd;
            endReg.lastIndex = 0;

            // Clip maskedSrc to same section of string as src (move to lexer?)
            maskedSrc = maskedSrc.slice(-1 * src.length + lLength);

            while ((match = endReg.exec(maskedSrc)) != null) {
                rDelim = match[1] || match[2] || match[3] || match[4] || match[5] || match[6];

                if (!rDelim) {
                    continue;
                } // skip single * in __abc*abc__

                rLength = [...rDelim].length;

                if (match[3] || match[4]) { // found another Left Delim
                    delimTotal += rLength;
                    continue;
                } else {
                    if (match[5] || match[6]) { // either Left or Right Delim
                        if (lLength % 3 && !((lLength + rLength) % 3)) {
                            midDelimTotal += rLength;
                            continue; // CommonMark Emphasis Rules 9-10
                        }
                    }
                }

                delimTotal -= rLength;

                if (delimTotal > 0) {
                    continue;
                } // Haven't found enough closing delimiters

                // Remove extra characters. *a*** -> *a*
                rLength = Math.min(rLength, rLength + delimTotal + midDelimTotal);
                // char length can be >1 for unicode characters;
                const lastCharLength = [...(match as any)[0]][0].length;
                const raw = src.slice(0, lLength + match.index + lastCharLength + rLength);

                // Create `em` if smallest delimiter has odd char count. *a***
                if (Math.min(lLength, rLength) % 2) {
                    const text = raw.slice(1, -1);
                    return {
                        type: 'em',
                        raw,
                        text,
                        tokens: this.lexer.inlineTokens(text),
                    };
                }

                // Create 'strong' if smallest delimiter has even char count. **a***
                const text = raw.slice(2, -2);
                return {
                    type: 'strong',
                    raw,
                    text,
                    tokens: this.lexer.inlineTokens(text),
                };
            }
        }
    }

    escape(src: string): Tokens.Escape | undefined {
        const cap = this.rules.inline.escape.exec(src);
        if (cap) {
            return {
                type: 'escape',
                raw: cap[0],
                text: escape(cap[1]),
            };
        }
    }

    fences(src: string): Tokens.Code | undefined {
        const cap = this.rules.block.fences.exec(src);
        if (cap) {
            const raw = cap[0];
            const text = indentCodeCompensation(raw, cap[3] || '');

            return {
                type: 'code',
                raw,
                lang: cap[2] ? cap[2].trim().replace(this.rules.inline.anyPunctuation, '$1') : cap[2],
                text,
            };
        }
    }

    heading(src: string): Tokens.Heading | undefined {
        const cap = this.rules.block.heading.exec(src);
        if (cap) {
            let text = cap[2].trim();

            // remove trailing #s
            if (/#$/.test(text)) {
                const trimmed = rtrim(text, '#');
                if (this.options.pedantic) {
                    text = trimmed.trim();
                } else {
                    if (!trimmed || / $/.test(trimmed)) {
                        // CommonMark requires space before trailing #s
                        text = trimmed.trim();
                    }
                }
            }

            return {
                type: 'heading',
                raw: cap[0],
                depth: cap[1].length,
                text,
                tokens: this.lexer.inline(text),
            };
        }
    }

    hr(src: string): Tokens.Hr | undefined {
        const cap = this.rules.block.hr.exec(src);
        if (cap) {
            return {
                type: 'hr',
                raw: cap[0],
            };
        }
    }

    html(src: string): Tokens.HTML | undefined {
        const cap = this.rules.block.html.exec(src);
        if (cap) {
            const token: Tokens.HTML = {
                type: 'html',
                block: true,
                raw: cap[0],
                pre: cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style',
                text: cap[0],
            };
            return token;
        }
    }

    inlineText(src: string): Tokens.Text | undefined {
        const cap = this.rules.inline.text.exec(src);
        if (cap) {
            let text;
            if (this.lexer.state.inRawBlock) {
                text = cap[0];
            } else {
                text = escape(cap[0]);
            }
            return {
                type: 'text',
                raw: cap[0],
                text,
            };
        }
    }

    lheading(src: string): Tokens.Heading | undefined {
        const cap = this.rules.block.lheading.exec(src);
        if (cap) {
            return {
                type: 'heading',
                raw: cap[0],
                depth: cap[2].charAt(0) === '=' ? 1 : 2,
                text: cap[1],
                tokens: this.lexer.inline(cap[1]),
            };
        }
    }

    link(src: string): Tokens.Link | Tokens.Image | undefined {
        const cap = this.rules.inline.link.exec(src);
        if (cap) {
            const trimmedUrl = cap[2].trim();
            if (!this.options.pedantic && /^</.test(trimmedUrl)) {
                // commonmark requires matching angle brackets
                if (!(/>$/.test(trimmedUrl))) {
                    return;
                }

                // ending angle bracket cannot be escaped
                const rtrimSlash = rtrim(trimmedUrl.slice(0, -1), '\\');
                if ((trimmedUrl.length - rtrimSlash.length) % 2 === 0) {
                    return;
                }
            } else {
                // find closing parenthesis
                const lastParenIndex = findClosingBracket(cap[2], '()');
                if (lastParenIndex > -1) {
                    const start = cap[0].indexOf('!') === 0 ? 5 : 4;
                    const linkLen = start + cap[1].length + lastParenIndex;
                    cap[2] = cap[2].substring(0, lastParenIndex);
                    cap[0] = cap[0].substring(0, linkLen).trim();
                    cap[3] = '';
                }
            }
            let href = cap[2];
            let title = '';
            if (this.options.pedantic) {
                // split pedantic href and title
                const link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href);

                if (link) {
                    href = link[1];
                    title = link[3];
                }
            } else {
                title = cap[3] ? cap[3].slice(1, -1) : '';
            }

            href = href.trim();
            if (/^</.test(href)) {
                if (this.options.pedantic && !(/>$/.test(trimmedUrl))) {
                    // pedantic allows starting angle bracket without ending angle bracket
                    href = href.slice(1);
                } else {
                    href = href.slice(1, -1);
                }
            }
            return outputLink(cap, {
                href: href ? href.replace(this.rules.inline.anyPunctuation, '$1') : href,
                title: title ? title.replace(this.rules.inline.anyPunctuation, '$1') : title,
            }, cap[0], this.lexer);
        }
    }

    list(src: string): Tokens.List | undefined {
        let cap = this.rules.block.list.exec(src);
        if (cap) {
            let bull = cap[1].trim();
            const isordered = bull.length > 1;

            const list: Tokens.List = {
                type: 'list',
                raw: '',
                ordered: isordered,
                start: isordered ? +bull.slice(0, -1) : '',
                loose: false,
                items: [],
            };

            bull = isordered ? `\\d{1,9}\\${bull.slice(-1)}` : `\\${bull}`;

            if (this.options.pedantic) {
                bull = isordered ? bull : '[*+-]';
            }

            // Get next list item
            const itemRegex = new RegExp(`^( {0,3}${bull})((?:[\t ][^\\n]*)?(?:\\n|$))`);
            let raw = '';
            let itemContents = '';
            let endsWithBlankLine = false;
            // Check if current bullet point can start a new List Item
            while (src) {
                let endEarly = false;
                if (!(cap = itemRegex.exec(src))) {
                    break;
                }

                if (this.rules.block.hr.test(src)) { // End list if bullet was actually HR (possibly move into itemRegex?)
                    break;
                }

                raw = cap[0];
                src = src.substring(raw.length);

                let line = cap[2].split('\n', 1)[0].replace(/^\t+/, (t: string) => ' '.repeat(3 * t.length));
                let nextLine = src.split('\n', 1)[0];

                let indent = 0;
                if (this.options.pedantic) {
                    indent = 2;
                    itemContents = line.trimStart();
                } else {
                    indent = cap[2].search(/[^ ]/); // Find first non-space char
                    indent = indent > 4 ? 1 : indent; // Treat indented code blocks (> 4 spaces) as having only 1 indent
                    itemContents = line.slice(indent);
                    indent += cap[1].length;
                }

                let blankLine = false;

                if (!line && /^ *$/.test(nextLine)) { // Items begin with at most one blank line
                    raw += nextLine + '\n';
                    src = src.substring(nextLine.length + 1);
                    endEarly = true;
                }

                if (!endEarly) {
                    const nextBulletRegex = new RegExp(
                        `^ {0,${Math.min(3, indent - 1)}}(?:[*+-]|\\d{1,9}[.)])((?:[ \t][^\\n]*)?(?:\\n|$))`);
                    const hrRegex = new RegExp(
                        `^ {0,${Math.min(3, indent - 1)}}((?:- *){3,}|(?:_ *){3,}|(?:\\* *){3,})(?:\\n+|$)`);
                    const fencesBeginRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}(?:\`\`\`|~~~)`);
                    const headingBeginRegex = new RegExp(`^ {0,${Math.min(3, indent - 1)}}#`);

                    // Check if following lines should be included in List Item
                    while (src) {
                        const rawLine = src.split('\n', 1)[0];
                        nextLine = rawLine;

                        // Re-align to follow commonmark nesting rules
                        if (this.options.pedantic) {
                            nextLine = nextLine.replace(/^ {1,4}(?=( {4})*[^ ])/g, '  ');
                        }

                        // End list item if found code fences
                        if (fencesBeginRegex.test(nextLine)) {
                            break;
                        }

                        // End list item if found start of new heading
                        if (headingBeginRegex.test(nextLine)) {
                            break;
                        }

                        // End list item if found start of new bullet
                        if (nextBulletRegex.test(nextLine)) {
                            break;
                        }

                        // Horizontal rule found
                        if (hrRegex.test(src)) {
                            break;
                        }

                        if (nextLine.search(/[^ ]/) >= indent || !nextLine.trim()) { // Dedent if possible
                            itemContents += '\n' + nextLine.slice(indent);
                        } else {
                            // not enough indentation
                            if (blankLine) {
                                break;
                            }

                            // paragraph continuation unless last line was a different block level element
                            if (line.search(/[^ ]/) >= 4) { // indented code block
                                break;
                            }
                            if (fencesBeginRegex.test(line)) {
                                break;
                            }
                            if (headingBeginRegex.test(line)) {
                                break;
                            }
                            if (hrRegex.test(line)) {
                                break;
                            }

                            itemContents += '\n' + nextLine;
                        }

                        if (!blankLine && !nextLine.trim()) { // Check if current line is blank
                            blankLine = true;
                        }

                        raw += rawLine + '\n';
                        src = src.substring(rawLine.length + 1);
                        line = nextLine.slice(indent);
                    }
                }

                if (!list.loose) {
                    // If the previous item ended with a blank line, the list is loose
                    if (endsWithBlankLine) {
                        list.loose = true;
                    } else {
                        if (/\n *\n *$/.test(raw)) {
                            endsWithBlankLine = true;
                        }
                    }
                }

                let istask: RegExpExecArray | null = null;
                let ischecked: boolean | undefined;
                // Check for task list items
                if (this.options.gfm) {
                    istask = /^\[[ xX]\] /.exec(itemContents);
                    if (istask) {
                        ischecked = istask[0] !== '[ ] ';
                        itemContents = itemContents.replace(/^\[[ xX]\] +/, '');
                    }
                }

                list.items.push({
                    type: 'list_item',
                    raw,
                    task: !!istask,
                    checked: ischecked,
                    loose: false,
                    text: itemContents,
                    tokens: [],
                });

                list.raw += raw;
            }

            // Do not consume newlines at end of final item. Alternatively, make itemRegex *start* with any newlines to
            // simplify/speed up endsWithBlankLine logic
            list.items[list.items.length - 1].raw = raw.trimEnd();
            (list.items[list.items.length - 1]).text = itemContents.trimEnd();
            list.raw = list.raw.trimEnd();

            // Item child tokens handled here at end because we needed to have the final item to trim it first
            for (let i = 0; i < list.items.length; i++) {
                this.lexer.state.top = false;
                list.items[i].tokens = this.lexer.blockTokens(list.items[i].text, []);

                if (!list.loose) {
                    // Check if list should be loose
                    const spacers = list.items[i].tokens.filter(t => t.type === 'space');
                    const hasMultipleLineBreaks = spacers.length > 0 && spacers.some(t => /\n.*\n/.test(t.raw));

                    list.loose = hasMultipleLineBreaks;
                }
            }

            // Set all items to loose if list is loose
            if (list.loose) {
                for (let i = 0; i < list.items.length; i++) {
                    list.items[i].loose = true;
                }
            }

            return list;
        }
    }

    paragraph(src: string): Tokens.Paragraph | undefined {
        const cap = this.rules.block.paragraph.exec(src);
        if (cap) {
            const text = cap[1].charAt(cap[1].length - 1) === '\n'
                ? cap[1].slice(0, -1)
                : cap[1];
            return {
                type: 'paragraph',
                raw: cap[0],
                text,
                tokens: this.lexer.inline(text),
            };
        }
    }

    reflink(src: string, links: Links): Tokens.Link | Tokens.Image | Tokens.Text | undefined {
        let cap;
        if ((cap = this.rules.inline.reflink.exec(src))
            || (cap = this.rules.inline.nolink.exec(src))) {
            const linkString = (cap[2] || cap[1]).replace(/\s+/g, ' ');
            const link = links[linkString.toLowerCase()];
            if (!link) {
                const text = cap[0].charAt(0);
                return {
                    type: 'text',
                    raw: text,
                    text,
                };
            }
            return outputLink(cap, link, cap[0], this.lexer);
        }
    }

    space(src: string): Tokens.Space | undefined {
        const cap = this.rules.block.newline.exec(src);
        if (cap && cap[0].length > 0) {
            return {
                type: 'space',
                raw: cap[0],
            };
        }
    }

    table(src: string): Tokens.Table | undefined {
        const cap = this.rules.block.table.exec(src);
        if (!cap) {
            return;
        }

        if (!/[:|]/.test(cap[2])) {
            // delimiter row must have a pipe (|) or colon (:) otherwise it is a setext heading
            return;
        }

        const headers = splitCells(cap[1]);
        const aligns = cap[2].replace(/^\||\| *$/g, '').split('|');
        const rows = cap[3] && cap[3].trim() ? cap[3].replace(/\n[ \t]*$/, '').split('\n') : [];

        const item: Tokens.Table = {
            type: 'table',
            raw: cap[0],
            header: [],
            align: [],
            rows: [],
        };

        if (headers.length !== aligns.length) {
            // header and align columns must be equal, rows can be different.
            return;
        }

        for (const align of aligns) {
            if (/^ *-+: *$/.test(align)) {
                item.align.push('right');
            } else {
                if (/^ *:-+: *$/.test(align)) {
                    item.align.push('center');
                } else {
                    if (/^ *:-+ *$/.test(align)) {
                        item.align.push('left');
                    } else {
                        item.align.push(null);
                    }
                }
            }
        }

        for (const header of headers) {
            item.header.push({
                text: header,
                tokens: this.lexer.inline(header),
            });
        }

        for (const row of rows) {
            item.rows.push(splitCells(row, item.header.length).map(cell => {
                return {
                    text: cell,
                    tokens: this.lexer.inline(cell),
                };
            }));
        }

        return item;
    }

    tag(src: string): Tokens.Tag | undefined {
        const cap = this.rules.inline.tag.exec(src);
        if (cap) {
            if (!this.lexer.state.inLink && /^<a /i.test(cap[0])) {
                this.lexer.state.inLink = true;
            } else {
                if (this.lexer.state.inLink && /^<\/a>/i.test(cap[0])) {
                    this.lexer.state.inLink = false;
                }
            }
            if (!this.lexer.state.inRawBlock && /^<(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
                this.lexer.state.inRawBlock = true;
            } else {
                if (this.lexer.state.inRawBlock && /^<\/(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
                    this.lexer.state.inRawBlock = false;
                }
            }

            return {
                type: 'html',
                raw: cap[0],
                inLink: this.lexer.state.inLink,
                inRawBlock: this.lexer.state.inRawBlock,
                block: false,
                text: cap[0],
            };
        }
    }

    text(src: string): Tokens.Text | undefined {
        const cap = this.rules.block.text.exec(src);
        if (cap) {
            return {
                type: 'text',
                raw: cap[0],
                text: cap[0],
                tokens: this.lexer.inline(cap[0]),
            };
        }
    }

    url(src: string): Tokens.Link | undefined {
        let cap;
        if (cap = this.rules.inline.url.exec(src)) {
            let text, href;
            if (cap[2] === '@') {
                text = escape(cap[0]);
                href = 'mailto:' + text;
            } else {
                // do extended autolink path validation
                let prevCapZero;
                do {
                    prevCapZero = cap[0];
                    cap[0] = this.rules.inline._backpedal.exec(cap[0])?.[0] ?? '';
                }
                while (prevCapZero !== cap[0]);
                text = escape(cap[0]);
                if (cap[1] === 'www.') {
                    href = 'http://' + cap[0];
                } else {
                    href = cap[0];
                }
            }
            return {
                type: 'link',
                raw: cap[0],
                text,
                href,
                tokens: [
                    {
                        type: 'text',
                        raw: text,
                        text,
                    },
                ],
            };
        }
    }
}