Skip to content

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

7.0 KB
Raw Blame
#ifndef ANYDOC_H
#define ANYDOC_H

/* Warning: this file is generated by `cargo build -p anydoc-go`. Do not edit by hand. */

#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>

/**
 * Success.
 */
#define ERR_OK 0

/**
 * `ConvertError::Unsupported`.
 */
#define ERR_UNSUPPORTED 1

/**
 * `ConvertError::Malformed`.
 */
#define ERR_MALFORMED 2

/**
 * `ConvertError::Encrypted`.
 */
#define ERR_ENCRYPTED 3

/**
 * `ConvertError::ResourceLimit`.
 */
#define ERR_RESOURCE_LIMIT 4

/**
 * `ConvertError::MissingPart`.
 */
#define ERR_MISSING_PART 5

/**
 * `ConvertError::Io`.
 */
#define ERR_IO 6

/**
 * PDF was passed to `anydoc_to_document` (unsupported there).
 */
#define ERR_PDF_NO_MODEL 7

/**
 * Null pointer or invalid argument passed to the ABI.
 */
#define ERR_INVALID_ARG 8

/**
 * Unknown format name passed to the ABI.
 */
#define ERR_UNKNOWN_FORMAT 9

/**
 * `ConvertError::NeedsOcr`; page numbers are retained in the error detail.
 */
#define ERR_NEEDS_OCR 10

/**
 * C-side format tag. Stable; mirrors the Node/Python lowercase string names
 * via `format_name`. `ANYDOC_FORMAT_NONE` is the `Option::None` sentinel.
 */
#define ANYDOC_FORMAT_NONE -1

#define ANYDOC_FORMAT_DOC 0

#define ANYDOC_FORMAT_DOCX 1

#define ANYDOC_FORMAT_ODT 2

#define ANYDOC_FORMAT_PDF 3

#define ANYDOC_FORMAT_PPT 4

#define ANYDOC_FORMAT_PPTX 5

#define ANYDOC_FORMAT_RTF 6

#define ANYDOC_FORMAT_EPUB 7

#define ANYDOC_FORMAT_XLSX 8

#define ANYDOC_FORMAT_ODS 9

#define ANYDOC_FORMAT_ODP 10

#define ANYDOC_FORMAT_CSV 11

/**
 * Tag values for `Block` variants. Stable across versions; the Go side maps
 * these to the same lowercase string names the Node and Python bindings use.
 */
#define BLOCK_HEADING 0

#define BLOCK_PARAGRAPH 1

#define BLOCK_LIST 2

#define BLOCK_TABLE 3

#define BLOCK_QUOTE 4

#define BLOCK_CODE 5

#define BLOCK_RULE 6

#define BLOCK_MATH 7

#define INLINE_TEXT 0

#define INLINE_LINK 1

#define INLINE_IMAGE 2

#define INLINE_ANCHOR 3

#define INLINE_NOTEREF 4

#define INLINE_LINEBREAK 5

#define INLINE_MATH 6

#define INLINE_CHECKBOX 7

#define LINK_EXTERNAL 0

#define LINK_RELATIVE 1

#define LINK_ANCHOR 2

#define IMG_EXTERNAL 0

#define IMG_ASSET 1

#define IMG_UNAVAILABLE 2

#define MARKER_BULLET 0

#define MARKER_DECIMAL 1

#define MARKER_LOWER_ALPHA 2

#define MARKER_UPPER_ALPHA 3

#define MARKER_LOWER_ROMAN 4

#define MARKER_UPPER_ROMAN 5

#define TABLE_DATA 0

#define TABLE_LAYOUT 1

#define SLOT_ORIGIN 0

#define SLOT_COVERED 1

#define NOTE_FOOTNOTE 0

#define NOTE_ENDNOTE 1

/**
 * Detect the format from the content. Writes a format tag to `*out` (one of
 * `ANYDOC_FORMAT_*`), or `ANYDOC_FORMAT_NONE` when nothing matches.
 *
 * Returns `ERR_OK` on success (including no-match), `ERR_INVALID_ARG` on null
 * pointers.
 */
int anydoc_format_from_bytes(const uint8_t *bytes, uintptr_t len, int *out);

/**
 * The format a bare extension names (no leading dot). Writes a format tag to
 * `*out`, or `ANYDOC_FORMAT_NONE` when unrecognized.
 */
int anydoc_format_from_extension(const char *ext, int *out);

/**
 * The format a path's extension names. Writes a format tag to `*out`, or
 * `ANYDOC_FORMAT_NONE` when unrecognized.
 */
int anydoc_format_from_path(const char *path, int *out);

/**
 * Convert a document file to Markdown. The format is detected from the file
 * content, with the extension as the fallback for signature-less formats
 * (CSV).
 *
 * On success writes a `*mut c_char` to `*out_str` and its byte length to
 * `*out_len`. The caller must free the string with `anydoc_string_free`.
 */
int anydoc_to_markdown(const char *path, char **out_str, uintptr_t *out_len);

/**
 * Convert an in-memory document to Markdown. `format_tag` is one of the
 * `ANYDOC_FORMAT_*` constants, or `ANYDOC_FORMAT_NONE` to detect from the
 * content.
 */
int anydoc_to_markdown_bytes(const uint8_t *bytes,
                             uintptr_t len,
                             int format_tag,
                             char **out_str,
                             uintptr_t *out_len);

/**
 * Convert an in-memory document to Markdown with embedded images rewritten
 * as `![alt](images/image-N.ext)` so they keep their original positions.
 *
 * This is `to_document` + anydoc's official GFM serializer. Asset images are
 * first turned into `ImageSource::External` URLs; the serializer already
 * emits those as ordinary Markdown image links. PDF has no document model
 * and is converted the same way as `anydoc_to_markdown_bytes`.
 */
int anydoc_to_markdown_with_asset_links(const uint8_t *bytes,
                                        uintptr_t len,
                                        int format_tag,
                                        char **out_str,
                                        uintptr_t *out_len);

/**
 * Parse an in-memory document into the document model. `format_tag` is one of
 * the `ANYDOC_FORMAT_*` constants, or `ANYDOC_FORMAT_NONE` to detect from the
 * content.
 *
 * On success writes a heap-allocated byte buffer to `*out_buf` and its length
 * to `*out_len`. The buffer holds the flat serialization (see `model`). The
 * caller must free it with `anydoc_buffer_free`.
 *
 * Returns `ERR_PDF_NO_MODEL` for PDF input: PDF conversion produces Markdown
 * directly and has no document-model form. Use `anydoc_to_markdown_bytes`.
 */
int anydoc_to_document(const uint8_t *bytes,
                       uintptr_t len,
                       int format_tag,
                       uint8_t **out_buf,
                       uintptr_t *out_len);

/**
 * Parse once and return the original document model followed by asset-linked
 * Markdown in a single flat buffer. Free it with `anydoc_buffer_free`.
 * PDF has no document model and returns `ERR_PDF_NO_MODEL`.
 */
int anydoc_to_document_with_asset_links(const uint8_t *bytes,
                                        uintptr_t len,
                                        int format_tag,
                                        uint8_t **out_buf,
                                        uintptr_t *out_len);

/**
 * Free a string returned by `anydoc_to_markdown*` or `anydoc_last_error`.
 * Null is a no-op (the empty-string sentinel).
 */
void anydoc_string_free(char *s);

/**
 * Free a document buffer returned by `anydoc_to_document`. Null is a no-op.
 * `len` must be the length written to `*out_len` at allocation time; it is
 * validated against the header for safety.
 */
void anydoc_buffer_free(uint8_t *buf, uintptr_t len);

/**
 * Return the human-readable message for the last error on the current
 * thread. The returned `*mut c_char` is freshly allocated and must be freed
 * with `anydoc_string_free`. Returns null when there is no last error.
 */
char *anydoc_last_error(void);

/**
 * Return the lowercase name of a format tag, or null for an unknown tag.
 * The returned string must be freed with `anydoc_string_free`.
 */
char *anydoc_format_name(int tag);

/**
 * Parse a lowercase format name into a tag. Writes the tag to `*out`, or
 * `ANYDOC_FORMAT_NONE` when the name is unknown.
 */
int anydoc_format_from_name(const char *name, int *out);

#endif  /* ANYDOC_H */