Versions in this module Expand all Collapse all v0 v0.2.0 Jul 19, 2026 v0.1.0 May 28, 2026 Changes in this version + func ProcessHTMLWithDiag(ctx context.Context, htmlContent string, baseURL string) (*HTMLResult, *DiagnosticInfo, error) + type DiagnosticInfo struct + ContentLength int + ReadabilityOK bool + ReadabilityTitle string + StageAnchoredLen int + StageConvertLen int + StageExtractLen int + StageExtractSrc string + StageFinalLen int + StagePreCleanLen int + StructureTags map[string]int + type HTMLResult struct + Markdown string + Title string + func ProcessHTML(ctx context.Context, htmlContent string, baseURL string) (*HTMLResult, error) + type Options struct + FileOutputDir string + MaxContentLength int + MaxInlineChars int + MaxInlineLines int + Store StoreWriter + type Output struct + AgentHint string + ContType string + FilePath string + Markdown string + Mode string + StatusCode int + Summary string + Title string + TotalChars int + TotalLines int + func ProcessResponse(ctx context.Context, resp *http.Response, baseURL string, contentType string, ...) (*Output, error) + type PDFOptions struct + Heuristic bool + MaxPages int + type PDFParseError struct + Reason string + Source string + func (e *PDFParseError) Error() string + type PDFParseResult struct + Markdown string + Method string + PageCount int + SourcePath string + Title string + func ParsePDFBytes(ctx context.Context, data []byte, name string, opts PDFOptions) (*PDFParseResult, error) + func ParsePDFFile(ctx context.Context, filePath string, opts PDFOptions) (*PDFParseResult, error) + type StoreWriter interface + WriteMarkdown func(content string, title string, sourceURL string) (filePath string, totalLines int, totalChars int, summary string, err error) + WriteMarkdownFromReader func(r io.Reader, title string, sourceURL string) (filePath string, totalLines int, totalChars int, summary string, err error)
Go to main page