Aided stab at basic tokenizer and api setup.

internal/tokenizer/languages.go

@@ -0,0 +1,106 @@
+package tokenizer
+
+import "regexp"
+
+func (t *Tokenizer) initializeLanguages() {
+	t.addGoLanguage()
+	t.addJavaScriptLanguage()
+	t.addMarkdownLanguage()
+	t.addTextLanguage()
+}
+
+func (t *Tokenizer) addGoLanguage() {
+	t.languages["go"] = &Language{
+		Name: "go",
+		Rules: []Rule{
+			// Comments
+			{regexp.MustCompile(`//.*$`), "comment", 100},
+			{regexp.MustCompile(`/\*[\s\S]*?\*/`), "comment", 100},
+
+			// Strings
+			{regexp.MustCompile(`"(?:[^"\\]|\\.)*"`), "string", 90},
+			{regexp.MustCompile("`[^`]*`"), "string", 90},
+
+			// Keywords
+			{regexp.MustCompile(`\b(package|import|func|var|const|type|struct|interface|if|else|for|range|switch|case|default|return|break|continue|go|defer|chan|select)\b`), "keyword", 80},
+
+			// Types
+			{regexp.MustCompile(`\b(int|int8|int16|int32|int64|uint|uint8|uint16|uint32|uint64|float32|float64|string|bool|byte|rune|error)\b`), "type", 70},
+
+			// Numbers
+			{regexp.MustCompile(`\b\d+(\.\d+)?\b`), "number", 60},
+
+			// Functions
+			{regexp.MustCompile(`\b([a-zA-Z_][a-zA-Z0-9_]*)\s*\(`), "function", 50},
+
+			// Default
+			{regexp.MustCompile(`[a-zA-Z_][a-zA-Z0-9_]*`), "identifier", 10},
+		},
+	}
+}
+
+func (t *Tokenizer) addMarkdownLanguage() {
+	t.languages["markdown"] = &Language{
+		Name: "markdown",
+		Rules: []Rule{
+			// Headers
+			{regexp.MustCompile(`^#{1,6}\s+.*$`), "header", 100},
+
+			// Code blocks
+			{regexp.MustCompile("```[\\s\\S]*?```"), "code-block", 95},
+			{regexp.MustCompile("`[^`]+`"), "code-inline", 90},
+
+			// Bold/Italic
+			{regexp.MustCompile(`\*\*[^*]+\*\*`), "bold", 85},
+			{regexp.MustCompile(`\*[^*]+\*`), "italic", 80},
+
+			// Links
+			{regexp.MustCompile(`\[([^\]]+)\]\([^)]+\)`), "link", 75},
+
+			// Lists
+			{regexp.MustCompile(`^\s*[-*+]\s+`), "list-marker", 70},
+			{regexp.MustCompile(`^\s*\d+\.\s+`), "list-marker", 70},
+		},
+	}
+}
+
+func (t *Tokenizer) addJavaScriptLanguage() {
+	t.languages["javascript"] = &Language{
+		Name: "javascript",
+		Rules: []Rule{
+			// Comments
+			{regexp.MustCompile(`//.*$`), "comment", 100},
+			{regexp.MustCompile(`/\*[\s\S]*?\*/`), "comment", 100},
+
+			// Strings
+			{regexp.MustCompile(`"(?:[^"\\]|\\.)*"`), "string", 90},
+			{regexp.MustCompile(`'(?:[^'\\]|\\.)*'`), "string", 90},
+			{regexp.MustCompile("`(?:[^`\\]|\\.)*`"), "string", 90},
+
+			// Keywords
+			{regexp.MustCompile(`\b(const|let|var|function|return|if|else|for|while|do|switch|case|default|break|continue|try|catch|finally|throw|new|this|class|extends|import|export|from|async|await)\b`), "keyword", 80},
+
+			// Types/Built-ins
+			{regexp.MustCompile(`\b(Object|Array|String|Number|Boolean|Date|RegExp|Error|Promise)\b`), "type", 70},
+
+			// Numbers
+			{regexp.MustCompile(`\b\d+(\.\d+)?\b`), "number", 60},
+
+			// Functions
+			{regexp.MustCompile(`\b([a-zA-Z_$][a-zA-Z0-9_$]*)\s*\(`), "function", 50},
+
+			// Default
+			{regexp.MustCompile(`[a-zA-Z_$][a-zA-Z0-9_$]*`), "identifier", 10},
+		},
+	}
+}
+
+func (t *Tokenizer) addTextLanguage() {
+	t.languages["text"] = &Language{
+		Name: "text",
+		Rules: []Rule{
+			// Just return everything as text
+			{regexp.MustCompile(`.+`), "text", 1},
+		},
+	}
+}

internal/tokenizer/tokenizer.go

@@ -0,0 +1,125 @@
+package tokenizer
+
+import (
+	"regexp"
+	"strings"
+)
+
+type Token struct {
+	Type    string `json:"type"`    // "keyword", "string", "comment", etc.
+	Content string `json:"content"` // actual text
+	Start   int    `json:"start"`   // character position
+	End     int    `json:"end"`     // character position
+}
+
+type TokenizedLine struct {
+	LineNumber int     `json:"lineNumber"`
+	Tokens     []Token `json:"tokens"`
+	Raw        string  `json:"raw"` // original line content
+}
+
+type TokenizedDocument struct {
+	Language string          `json:"language"`
+	Lines    []TokenizedLine `json:"lines"`
+	Metadata DocumentMeta    `json:"metadata"`
+}
+
+type DocumentMeta struct {
+	TotalLines int    `json:"totalLines"`
+	FileSize   int64  `json:"fileSize"`
+	Language   string `json:"language"`
+}
+
+type Tokenizer struct {
+	languages map[string]*Language
+}
+
+type Language struct {
+	Name  string
+	Rules []Rule
+}
+
+type Rule struct {
+	Pattern  *regexp.Regexp
+	Token    string
+	Priority int // higher priority rules checked first
+}
+
+func NewTokenizer() *Tokenizer {
+	t := &Tokenizer{
+		languages: make(map[string]*Language),
+	}
+
+	// Initialize with basic languages
+	t.initializeLanguages()
+	return t
+}
+
+func (t *Tokenizer) TokenizeDocument(content, language string) *TokenizedDocument {
+	lines := strings.Split(content, "\n")
+	tokenizedLines := make([]TokenizedLine, len(lines))
+
+	lang := t.languages[language]
+	if lang == nil {
+		lang = t.languages["text"] // fallback
+	}
+
+	for i, line := range lines {
+		tokenizedLines[i] = TokenizedLine{
+			LineNumber: i + 1,
+			Tokens:     t.tokenizeLine(line, lang),
+			Raw:        line,
+		}
+	}
+
+	return &TokenizedDocument{
+		Language: language,
+		Lines:    tokenizedLines,
+		Metadata: DocumentMeta{
+			TotalLines: len(lines),
+			FileSize:   int64(len(content)),
+			Language:   language,
+		},
+	}
+}
+
+func (t *Tokenizer) tokenizeLine(line string, lang *Language) []Token {
+	if len(line) == 0 {
+		return []Token{}
+	}
+
+	var tokens []Token
+	remaining := line
+	offset := 0
+
+	for len(remaining) > 0 {
+		matched := false
+
+		// Try each rule in priority order
+		for _, rule := range lang.Rules {
+			if loc := rule.Pattern.FindStringIndex(remaining); loc != nil && loc[0] == 0 {
+				// Found a match at the beginning
+				matchText := remaining[loc[0]:loc[1]]
+				tokens = append(tokens, Token{
+					Type:    rule.Token,
+					Content: matchText,
+					Start:   offset,
+					End:     offset + len(matchText),
+				})
+
+				remaining = remaining[loc[1]:]
+				offset += loc[1]
+				matched = true
+				break
+			}
+		}
+
+		if !matched {
+			// No rule matched, skip one character
+			remaining = remaining[1:]
+			offset++
+		}
+	}
+
+	return tokens
+}