Last active
November 9, 2017 07:36
-
-
Save u1735067/9c803a37be34e99600ccc1302a69bfdc to your computer and use it in GitHub Desktop.
MOBI & PDB (Palm DataBase) container in kaitai lang
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| meta: | |
| id: mobi | |
| file-extension: mobi | |
| endian: be | |
| # https://wiki.mobileread.com/wiki/MOBI | |
| seq: | |
| - id: pdb_header | |
| type: pdb_header_type | |
| size: 78 # 0x4e | |
| - id: pdb_record_index | |
| type: pdb_record_index_type | |
| repeat: expr | |
| repeat-expr: pdb_header.num_records | |
| # type: ressource_index | |
| - id: zeros # Padding probably | |
| contents: [ 0x00, 0x00 ] | |
| - id: record0 | |
| type: record0_type | |
| size: pdb_record_index[1].offset - pdb_record_index[0].offset | |
| types: | |
| # https://wiki.mobileread.com/wiki/PDB#Palm_Database_Format | |
| # https://en.wikipedia.org/wiki/PDB_(Palm_OS) | |
| # https://github.com/sumatrapdfreader/sumatrapdf/blob/master/src/utils/PalmDbReader.h | |
| # https://github.com/alphabetum/kindler/tree/master/lib/palm | |
| pdb_header_type: | |
| seq: | |
| - id: name | |
| type: strz | |
| encoding: cp1252 | |
| size: 0x20 # 31+0x0 | |
| - id: attributes | |
| # https://github.com/alphabetum/kindler/blob/master/lib/palm/pdb.rb | |
| type: u2 | |
| - id: version | |
| type: u2 | |
| - id: creation_time | |
| type: u4 | |
| - id: modification_time | |
| type: u4 | |
| - id: backup_time | |
| type: u4 | |
| - id: modification_number | |
| type: u4 | |
| - id: app_info_offset | |
| type: u4 | |
| - id: sort_info_offset | |
| type: u4 | |
| - id: type | |
| size: 4 | |
| type: str | |
| encoding: ascii | |
| - id: creator | |
| size: 4 | |
| type: str | |
| encoding: ascii | |
| - id: unique_id | |
| type: u4 | |
| - id: next_record | |
| type: u4 | |
| - id: num_records | |
| type: u2 | |
| #instances: | |
| # type_creator: | |
| # value: type + creator | |
| # enum: pdb_type_enum | |
| pdb_record_index_type: | |
| seq: | |
| - id: offset | |
| type: u4 | |
| - id: packed_attributes | |
| type: pdb_record_index_attribute_type | |
| # Initially in the form id_{a,b,c} .. but num_records is only 2 bytes .. so ? | |
| # But next_record is 4 bits ? What if they're both 3 bits actually ? | |
| - id: id_h | |
| type: u1 | |
| - id: id_l | |
| type: u2 | |
| instances: | |
| id: | |
| value: (id_h << 16) | id_l # (id_h << 16) + id_l | |
| # content: | |
| # io: _root._io | |
| # pos: offset | |
| # size: _parent.pdb_record_index[_index+1] - offset | |
| pdb_record_index_attribute_type: # bitmap | |
| seq: | |
| - id: unknow | |
| type: b4 | |
| - id: expunged | |
| type: b1 | |
| - id: dirty | |
| type: b1 | |
| - id: deleted | |
| type: b1 | |
| - id: private | |
| type: b1 | |
| record0_type: | |
| seq: | |
| - id: palm_doc_header | |
| type: palm_doc_header_type | |
| - id: mobi_header | |
| type: mobi_header_type | |
| - id: exth_header | |
| type: exth_header_type | |
| if: mobi_header.content.common.exth_flags.has_exth | |
| - id: rest | |
| size-eos: true | |
| palm_doc_header_type: | |
| seq: | |
| - id: compression | |
| type: u2 | |
| enum: palm_doc_compression_enum | |
| - id: zeros | |
| contents: [ 0x00, 0x00 ] | |
| - id: text_length | |
| type: u4 | |
| - id: record_count | |
| type: u2 | |
| - id: record_size | |
| type: u2 | |
| - id: encryption | |
| type: u2 | |
| enum: palm_doc_encryption_enum | |
| - id: unknow # Probably padding too | |
| type: u2 | |
| mobi_header_type: | |
| seq: | |
| - id: identifier | |
| size: 4 | |
| type: str | |
| encoding: ascii | |
| - id: header_length # Calibre uses 0x8e (142) for v2/6 and 0x108 (264) for v8 | |
| type: u4 | |
| - id: content | |
| type: mobi_header_content_type | |
| size: header_length - 8 | |
| # https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/writer2/main.py | |
| # https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/writer8/mobi.py | |
| # https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/debug/headers.py | |
| mobi_header_content_type: | |
| seq: | |
| - id: common | |
| type: mobi_header_content_common_type | |
| # Is http://www.fabiszewski.net/libmobi/group__mobi__len.html correct ? | |
| - id: extra_v6 | |
| type: mobi_header_content_extra_v6_type | |
| if: common.format_version >= 6 | |
| - id: content_extra_v7 | |
| type: mobi_header_content_extra_v7_type | |
| #if: common.format_version == 7 | |
| if: _parent.header_length - 8 - _io.pos == 16 # There's mobi that advertises format v7 but doesn't have this .. | |
| - id: content_extra_v8 | |
| type: mobi_header_content_extra_v8_type | |
| #if: common.format_version >= 8 | |
| if: _parent.header_length - 8 - _io.pos == 32 | |
| - id: rest | |
| size-eos: true | |
| mobi_header_content_common_type: | |
| seq: | |
| - id: book_type | |
| type: u4 | |
| enum: mobi_type_enum | |
| - id: text_encoding | |
| type: u4 | |
| enum: mobi_text_encoding_enum | |
| - id: unique_id | |
| type: u4 | |
| - id: format_version | |
| type: u4 | |
| - id: ortographic_record | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: inflection_record | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: index_names # Aka secondary_index_record | |
| type: u4 | |
| doc: "Index number or 0xFFFFFFFF" | |
| - id: index_keys # Aka reserved | |
| type: u4 | |
| doc: "Index number or 0xFFFFFFFF" | |
| - id: extra_index_0 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: extra_index_1 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: extra_index_2 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: extra_index_3 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: extra_index_4 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: extra_index_5 | |
| type: u4 | |
| doc: "Section index number or 0xFFFFFFFF" | |
| - id: first_non_text_record | |
| type: u4 | |
| - id: title_offset | |
| type: u4 | |
| doc: "Offset in record0" | |
| - id: title_length | |
| type: u4 | |
| - id: language | |
| type: u4 | |
| enum: ms_lcid_enum | |
| - id: dictionnary_input_language | |
| type: u4 | |
| enum: ms_lcid_enum | |
| - id: dictionnary_output_language | |
| type: u4 | |
| enum: ms_lcid_enum | |
| - id: min_version | |
| type: u4 | |
| - id: first_ressource_record | |
| type: u4 | |
| - id: huffman_record | |
| type: u4 | |
| - id: huffman_record_count | |
| type: u4 | |
| - id: huffman_table_record # Aka datp_record | |
| type: u4 | |
| - id: huffman_table_record_count # Aka datp_record_count | |
| type: u4 | |
| - id: exth_flags | |
| type: mobi_header_content_common_exth_flags_type | |
| doc: "bit6 / 0x40 > there's an EXTH record" | |
| # Might cut here for files without DRM | |
| - id: unknow1 | |
| size: 32 | |
| - id: unknow2 | |
| type: u4 | |
| - id: drm_offset | |
| type: u4 | |
| doc: "Starting from record0" | |
| - id: drm_count | |
| type: u4 | |
| - id: drm_size | |
| type: u4 | |
| - id: drm_flags | |
| type: u4 | |
| # Might cut here for files without extra data | |
| - id: unknow3 | |
| type: u8 | |
| doc: "Bytes to the end of the MOBI header, including the following if the header length >= 228 (244 from start of record)." | |
| - id: first_content_record | |
| type: u2 | |
| if: format_version < 7 | |
| - id: content_last_index_number | |
| type: u2 | |
| doc: "Includes images, DATP, HUFF, DRM" | |
| if: format_version < 7 | |
| - id: fdst_record | |
| type: u4 | |
| if: format_version >= 7 | |
| - id: fdst_record_count | |
| type: u4 | |
| - id: fcis_record | |
| type: u4 | |
| - id: fcis_record_count | |
| type: u4 | |
| - id: flis_record | |
| type: u4 | |
| - id: flis_record_count | |
| type: u4 | |
| - id: unknow4 | |
| type: u8 | |
| mobi_header_content_common_exth_flags_type: # bitfield | |
| doc-ref: "https://github.com/kovidgoyal/calibre/blob/e333001d31dc49102fe5178bd2a8af4f06962fac/src/calibre/ebooks/mobi/writer2/main.py#L301" | |
| doc-ref: "https://github.com/kovidgoyal/calibre/blob/875af72918c71871e17897b5e8d13e556f6ddf17/src/calibre/ebooks/mobi/writer8/mobi.py#L293" | |
| seq: | |
| - id: unknow1 | |
| type: u2 | |
| - id: unknow2 | |
| type: b3 | |
| - id: has_fonts # 0b1_0000_0000_0000 | |
| type: b1 | |
| - id: unknow3 | |
| type: b5 | |
| - id: has_exth # 0b100_0000 | |
| type: b1 | |
| - id: unknow4 | |
| type: b1 | |
| - id: unknow5 # 0b1_0000 , used by calibre | |
| type: b1 | |
| - id: periodical # 0b1000 | |
| type: b1 | |
| - id: unknow6 | |
| type: b3 | |
| mobi_header_content_extra_v6_type: | |
| seq: | |
| - id: srcs_record # Aka compilation_data_section_first_count | |
| type: u4 | |
| - id: srcs_record_count # Aka compilation_data_section_count | |
| type: u4 | |
| - id: unknow5 | |
| type: u8 | |
| - id: extra_data_flags | |
| type: mobi_header_content_extra_v6_extra_data_type | |
| doc-ref: "https://github.com/kovidgoyal/calibre/blob/875af72918c71871e17897b5e8d13e556f6ddf17/src/calibre/ebooks/mobi/writer8/mobi.py#L166" | |
| - id: ncx_record # Aka primary_index_record_idx | |
| type: u4 | |
| mobi_header_content_extra_v6_extra_data_type: # bitfield | |
| seq: | |
| - id: unknow1 | |
| type: u2 | |
| - id: unknow2 | |
| type: u1 | |
| - id: unknow3 | |
| type: b5 | |
| - id: uncrossable_breaks # 0b100 - uncrossable breaks only used in MOBI 6 | |
| type: b1 | |
| - id: tbs_indexing_data # 0b010 - TBS indexing data (only used in MOBI 6) | |
| type: b1 | |
| - id: extra_multibyte # 0b001 - extra multibyte bytes after text records | |
| type: b1 | |
| # Maybe just the start of the v8 version | |
| mobi_header_content_extra_v7_type: | |
| seq: | |
| - id: unknow | |
| size: 16 | |
| mobi_header_content_extra_v8_type: | |
| seq: | |
| - id: chunk_record | |
| type: u4 | |
| - id: skel_record | |
| type: u4 | |
| - id: datp_record | |
| type: u4 | |
| - id: guide_record | |
| type: u4 | |
| - id: unknow1 | |
| type: u4 | |
| - id: unknow2 | |
| type: u4 | |
| - id: unknow3 | |
| type: u4 | |
| - id: unknow4 | |
| type: u4 | |
| exth_header_type: | |
| seq: | |
| - id: identifier | |
| size: 4 | |
| type: str | |
| encoding: ascii | |
| - id: header_length | |
| type: u4 | |
| - id: record_count | |
| type: u4 | |
| - id: records | |
| type: exth_records_type | |
| size: header_length-12 | |
| exth_records_type: | |
| seq: | |
| - id: record | |
| type: exth_record_type | |
| repeat: expr | |
| repeat-expr: _parent.record_count | |
| - id: padding | |
| size-eos: true | |
| exth_record_type: | |
| meta: | |
| #encoding: _root.record0.mobi_header.content.common.text_encoding | |
| encoding: UTF8 | |
| instances: | |
| data_length: | |
| value: length - 8 | |
| seq: | |
| - id: type | |
| type: u4 | |
| enum: exth_record_type_enum | |
| - id: length | |
| type: u4 | |
| - id: data | |
| size: length - 8 | |
| type: | |
| switch-on: type | |
| cases: | |
| exth_record_type_enum::drm_ebookbase_book_id: str | |
| exth_record_type_enum::title: str | |
| exth_record_type_enum::creator: str | |
| exth_record_type_enum::publisher: str | |
| exth_record_type_enum::imprint: str | |
| exth_record_type_enum::description: str | |
| exth_record_type_enum::isbn: str | |
| exth_record_type_enum::subject: str | |
| exth_record_type_enum::published: str | |
| exth_record_type_enum::review: str | |
| exth_record_type_enum::contributor: str | |
| exth_record_type_enum::rights: str | |
| exth_record_type_enum::type: str | |
| exth_record_type_enum::source: str | |
| exth_record_type_enum::asin_id_113: str | |
| #exth_record_type_enum::version_number: str | |
| #exth_record_type_enum::price: str | |
| #exth_record_type_enum::currency: str | |
| #exth_record_type_enum::book_type: str | |
| exth_record_type_enum::kf8_count_of_resources_fonts_images: u4 | |
| exth_record_type_enum::kf8_masthead__cover_image: str | |
| exth_record_type_enum::dict_short_name: str | |
| exth_record_type_enum::creator_major_version: u4 | |
| exth_record_type_enum::creator_minor_version: u4 | |
| exth_record_type_enum::creator_build_number: u4 | |
| #exth_record_type_enum::watermark: str | |
| exth_record_type_enum::cde_type: str # Heard it can be hex | |
| exth_record_type_enum::updated_title: str | |
| exth_record_type_enum::asin_id_504: str | |
| exth_record_type_enum::language: str | |
| exth_record_type_enum::primary_writing_mode: str | |
| exth_record_type_enum::creator_string: str | |
| exth_record_type_enum::override_kindle_fonts: str | |
| exth_record_type_enum::kindle_source_desc: str | |
| exth_record_type_enum::input_source_type: str | |
| exth_record_type_enum::kindlegen_build_rev_number: str | |
| enums: | |
| # pdb_type_enum: | |
| # https://github.com/kovidgoyal/calibre/blob/master/format_docs/pdb/pdb_types.txt | |
| # "'.pdfADBE'": adobe_reader | |
| # "'TEXtREAd'": palm_doc | |
| # "'BVokBDIC'": b_dicty | |
| # "'DB99DBOS'": db # (Database program) | |
| # "'PNRdPPrs'": e_reader | |
| # "'DataPPrs'": e_reader | |
| # "'vIMGView'": fire_viewer # (ImageViewer) | |
| # "'PmDBPmDB'": han_dbase | |
| # "'InfoINDB'": info_view | |
| # "'ToGoToGo'": i_silo | |
| # "'SDocSilX'": i_silo_3 | |
| # "'JbDbJBas'": j_file | |
| # "'JfDbJFil'": j_file_pro | |
| # "'DATALSdb'": list | |
| # "'Mdb1Mdb1'": mobile_db | |
| # "'BOOKMOBI'": mobi_pocket | |
| # "'DataPlkr'": plucker | |
| # "'DataSprd'": quick_sheet | |
| # "'SM01SMem'": super_memo | |
| # "'TEXtTlDc'": teal_doc | |
| # "'InfoTlIf'": teal_info | |
| # "'DataTlMl'": teal_meal | |
| # "'DataTlPt'": teal_paint | |
| # "'dataTDBP'": think_db | |
| # "'TdatTide'": tides | |
| # "'ToRaTRPW'": tome_raider | |
| # "'zTXTGPlm'": weasel | |
| # "'BDOCWrdS'": word_smith | |
| palm_doc_compression_enum: | |
| 1: no | |
| 2: palm_doc_compression | |
| 17480: huff_cdic_compression | |
| palm_doc_encryption_enum: | |
| 0: unencrypted | |
| 1: old_mobipocket_encryption | |
| 2: mobipocket_encryption | |
| mobi_type_enum: | |
| 002: mobipocket_book # Chapter / chapter nav | |
| 003: palmdoc_book | |
| 004: audio | |
| 232: mobipocket_kindle_gen1_2 | |
| 248: kf8_kindle_gen2 | |
| 257: news # News hierarchical | |
| 258: news_feed # News (flat) | |
| 259: news_magazine | |
| 513: pics | |
| 514: word | |
| 515: xls | |
| 516: ppt | |
| 517: text | |
| 518: html | |
| mobi_text_encoding_enum: | |
| 01252: cp1252 | |
| 65001: utf8 | |
| 65002: utf16 # http://www.fabiszewski.net/libmobi/group__mobi__enc.html | |
| exth_record_type_enum: | |
| # https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/writer8/exth.py | |
| # http://www.fabiszewski.net/libmobi/group__mobi__enums.html | |
| 001: drm_server_id | |
| 002: drm_commerce_id | |
| 003: drm_ebookbase_book_id | |
| 099: title | |
| 100: creator | |
| 101: publisher | |
| 102: imprint | |
| 103: description | |
| 104: isbn | |
| 105: subject | |
| 106: published | |
| 107: review | |
| 108: contributor | |
| 109: rights | |
| 110: subject_code | |
| 111: type | |
| 112: source | |
| 113: asin_id_113 | |
| 114: version_number | |
| 115: sample | |
| 116: start_offset # STARTREADING | |
| 117: adult | |
| 118: price | |
| 119: currency | |
| 121: kf8_boundary_section # KF8BOUNDARY | |
| 122: fixed_layout | |
| 123: book_type | |
| 124: orientation_lock | |
| 125: kf8_count_of_resources_fonts_images # COUNTRESOURCES | |
| 126: original_resolution | |
| 127: zero_gutter | |
| 128: zero_margin | |
| 129: kf8_masthead__cover_image # KF8COVERURI | |
| 131: kf8_unidentified_count # RESCOFFSET | |
| 132: region_magnification | |
| 200: dict_short_name | |
| 201: cover_offset | |
| 202: thum_boffset | |
| 203: fake_cover | |
| 204: creator_software # http://www.fabiszewski.net/libmobi/common_8c-example.html | |
| 205: creator_major_version | |
| 206: creator_minor_version | |
| 207: creator_build_number | |
| 208: watermark | |
| 209: tamper_proof_keys # [hex] | |
| 300: font_signature # [hex] | |
| 301: clipping_limit # [3xx] | |
| 401: clipping_limit | |
| 402: publisher_limit | |
| 404: text_to_speech_disabled | |
| 406: rental # libmobi | |
| 501: cde_type # DOCTYPE | |
| 502: last_update_time | |
| 503: updated_title | |
| 504: asin_id_504 # [5xx] | |
| 508: unknown_title_furigana | |
| 517: unknown_creator_furigana | |
| 522: unknown_publisher_furigana | |
| 524: language | |
| 525: primary_writing_mode # ALIGNMENT | |
| 526: creator_string # libmobi | |
| 527: page_progression_direction | |
| 528: override_kindle_fonts | |
| 529: kindle_source_desc #libmobi | |
| 531: dict_lang_in #libmobi | |
| 532: dict_lang_out #libmobi | |
| 534: input_source_type | |
| 535: kindlegen_build_rev_number | |
| 536: container_info | |
| 538: container_resolution | |
| 539: container_mimetype | |
| 543: container_id | |
| ms_lcid_enum: | |
| # https://github.com/libyal/libfwnt/wiki/Language-Code-identifiers | |
| # https://msdn.microsoft.com/en-us/library/cc233965.aspx | |
| # https://msdn.microsoft.com/en-us/library/cc233982.aspx | |
| # https://msdn.microsoft.com/en-us/library/cc233968.aspx | |
| # https://msdn.microsoft.com/en-us/library/windows/desktop/dd318693(v=vs.85).aspx | |
| # https://github.com/Alexpux/mingw-w64/blob/master/mingw-w64-headers/include/winnt.h#L1250 | |
| # https://github.com/evernote/serge/blob/master/lib/Serge/Util/LangID.pm | |
| # https://www.autoitscript.fr/autoit3/docs/appendix/OSLangCodes.htm | |
| # https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/langcodes.py | |
| 0x00: none | |
| 0x7F: invariant | |
| 0x02: system_default | |
| 0x36: afrikaans | |
| 0x1c: albanian | |
| 0x84: alsatian | |
| 0x5E: amharic | |
| 0x01: arabic | |
| 0x2B: armenian | |
| 0x4D: assamese | |
| 0x2C: azeri | |
| 0x45: bangla | |
| 0x6D: bashkir | |
| 0x2d: basque | |
| 0x23: belarusian | |
| 0x1A: bosnian | |
| 0x7E: breton | |
| 0x02: bulgarian | |
| 0x92: central_kurdish | |
| 0x5C: cherokee | |
| 0x03: catalan | |
| 0x04: chinese | |
| 0x04: chinese_simplified | |
| 0x83: corsican | |
| 0x1A: croatian | |
| 0x1a: croatian | |
| 0x05: czech | |
| 0x06: danish | |
| 0x8C: dari | |
| 0x65: divehi | |
| 0x13: dutch | |
| 0x09: english | |
| 0x25: estonian | |
| 0x38: faeroese | |
| 0x64: filipino | |
| 0x0B: finnish | |
| 0x0C: french | |
| 0x62: frisian | |
| 0x56: galician | |
| 0x37: georgian | |
| 0x07: german | |
| 0x08: greek | |
| 0x6F: greenlandic | |
| 0x47: gujarati | |
| 0x68: hausa | |
| 0x75: hawaiian | |
| 0x0D: hebrew | |
| 0x39: hindi | |
| 0x0E: hungarian | |
| 0x0F: icelandic | |
| 0x70: igbo | |
| 0x21: indonesian | |
| 0x5D: inuktitut | |
| 0x3C: irish | |
| 0x34: xhosa | |
| 0x35: zulu | |
| 0x10: italian | |
| 0x11: japanese | |
| 0x4B: kannada | |
| 0x60: kashmiri | |
| 0x3F: kazak | |
| 0x53: khmer | |
| 0x86: kiche | |
| 0x87: kinyarwanda | |
| 0x57: konkani | |
| 0x12: korean | |
| 0x40: kyrgyz | |
| 0x54: lao | |
| 0x26: latvian | |
| 0x27: lithuanian | |
| 0x2E: lower_sorbian | |
| 0x6E: luxembourgish | |
| 0x2F: macedonian | |
| 0x3E: malay | |
| 0x4C: malayalam | |
| 0x3A: maltese | |
| 0x58: manipuri | |
| 0x81: maori | |
| 0x7A: mapudungun | |
| 0x4E: marathi | |
| 0x7C: mohawk | |
| 0x50: mongolian | |
| 0x61: nepali | |
| 0x14: norwegian | |
| 0x82: occitan | |
| 0x48: oriya | |
| 0x63: pashto | |
| 0x29: persian | |
| 0x15: polish | |
| 0x16: portuguese | |
| 0x67: pular | |
| 0x46: punjabi | |
| 0x6B: quechua | |
| 0x18: romanian | |
| 0x17: romansh | |
| 0x19: russian | |
| 0x85: sakha | |
| 0x3B: sami | |
| 0x4F: sanskrit | |
| 0x1a: serbian | |
| 0x6C: sotho | |
| 0x32: tswana | |
| 0x59: sindhi | |
| 0x5B: sinhalese | |
| 0x1b: slovak | |
| 0x24: slovenian | |
| 0x0A: spanish | |
| 0x41: swahili | |
| 0x1D: swedish | |
| 0x5A: syriac | |
| 0x28: tajik | |
| 0x5F: tamazight | |
| 0x49: tamil | |
| 0x44: tatar | |
| 0x4A: telugu | |
| 0x1E: thai | |
| 0x51: tibetan | |
| 0x73: tigrinya | |
| 0x73: tigrigna | |
| 0x1F: turkish | |
| 0x42: turkmen | |
| 0x22: ukrainian | |
| 0x2E: upper_sorbian | |
| 0x20: urdu | |
| 0x80: uighur | |
| 0x43: uzbek | |
| 0x03: valencian | |
| 0x2A: vietnamese | |
| 0x52: welsh | |
| 0x88: wolof | |
| 0x78: yi | |
| 0x6A: yoruba | |
| 0x0C00: custom_default | |
| 0x1400: ui_custom_default | |
| 0x007F: neutral | |
| 0x0800: sys_default | |
| 0x1000: custom_unspecified | |
| 0x0400: default | |
| 0x0436: afrikaans_south_africa | |
| 0x041C: albanian_albania | |
| 0x0484: alsatian_france | |
| 0x045E: amharic_ethiopia | |
| 0x1401: arabic_algeria | |
| 0x3C01: arabic_bahrain | |
| 0x0C01: arabic_egypt | |
| 0x0801: arabic_iraq | |
| 0x2C01: arabic_jordan | |
| 0x3401: arabic_kuwait | |
| 0x3001: arabic_lebanon | |
| 0x1001: arabic_libya | |
| 0x1801: arabic_morocco | |
| 0x2001: arabic_oman | |
| 0x4001: arabic_qatar | |
| 0x0401: arabic_saudi_arabia | |
| 0x2801: arabic_syria | |
| 0x1C01: arabic_tunisia | |
| 0x3801: arabic_uae | |
| 0x2401: arabic_yemen | |
| 0x042B: armenian_armenia | |
| 0x044D: assamese_india | |
| 0x082C: azeri_cyrillic | |
| 0x042C: azeri_latin | |
| 0x0445: bangla_bangladesh | |
| 0x046D: bashkir_russia | |
| 0x042D: basque_basque | |
| 0x0423: belarusian_belarus | |
| 0x781A: bosnian_neutral | |
| 0x201A: bosnian_bosnia_herzegovina_cyrillic | |
| 0x141A: bosnian_bosnia_herzegovina_latin | |
| 0x047E: breton_france | |
| 0x0402: bulgarian_bulgaria | |
| 0x0492: central_kurdish_iraq | |
| 0x045C: cherokee_cherokee | |
| 0x0403: catalan_catalan | |
| 0x0C04: chinese_hongkong | |
| 0x1404: chinese_macau | |
| 0x1004: chinese_singapore | |
| 0x0004: chinese_simplified | |
| 0x7C04: chinese_traditional | |
| 0x0483: corsican_france | |
| 0x001A: croatian_neutral | |
| 0x101A: croatian_bosnia_herzegovina_latin | |
| 0x041A: croatian_croatia | |
| 0x0405: czech_czech_republic | |
| 0x0406: danish_denmark | |
| 0x048C: dari_afghanistan | |
| 0x0465: divehi_maldives | |
| 0x0813: dutch_belgian | |
| 0x0413: dutch | |
| 0x0C09: english_aus | |
| 0x2809: english_belize | |
| 0x1009: english_can | |
| 0x2409: english_caribbean | |
| 0x4009: english_india | |
| 0x1809: english_eire | |
| 0x1809: english_ireland | |
| 0x2009: english_jamaica | |
| 0x4409: english_malaysia | |
| 0x1409: english_nz | |
| 0x3409: english_philippines | |
| 0x4809: english_singapore | |
| 0x1c09: english_south_africa | |
| 0x2C09: english_trinidad | |
| 0x0809: english_uk | |
| 0x0409: english_us | |
| 0x3009: english_zimbabwe | |
| 0x0425: estonian_estonia | |
| 0x0438: faeroese_faroe_islands | |
| 0x0464: filipino_philippines | |
| 0x040B: finnish_finland | |
| 0x080c: french_belgian | |
| 0x0C0C: french_canadian | |
| 0x040c: french | |
| 0x140C: french_luxembourg | |
| 0x180C: french_monaco | |
| 0x100C: french_swiss | |
| 0x0462: frisian_netherlands | |
| 0x0456: galician_galician | |
| 0x0437: georgian_georgia | |
| 0x0C07: german_austrian | |
| 0x0407: german | |
| 0x1407: german_liechtenstein | |
| 0x1007: german_luxembourg | |
| 0x0807: german_swiss | |
| 0x0408: greek_greece | |
| 0x046F: greenlandic_greenland | |
| 0x0447: gujarati_india | |
| 0x0468: hausa_nigeria_latin | |
| 0x0475: hawaiian_us | |
| 0x040D: hebrew_israel | |
| 0x0439: hindi_india | |
| 0x040E: hungarian_hungary | |
| 0x040F: icelandic_iceland | |
| 0x0470: igbo_nigeria | |
| 0x0421: indonesian_indonesia | |
| 0x085D: inuktitut_canada_latin | |
| 0x045D: inuktitut_canada | |
| 0x083C: irish_ireland | |
| 0x0434: xhosa_south_africa | |
| 0x0435: zulu_south_africa | |
| 0x0410: italian | |
| 0x0810: italian_swiss | |
| 0x0411: japanese_japan | |
| 0x044B: kannada_india | |
| 0x043F: kazak_kazakhstan | |
| 0x0453: khmer_cambodia | |
| 0x0486: kiche_guatemala | |
| 0x0487: kinyarwanda_rwanda | |
| 0x0457: konkani_india | |
| 0x0412: korean | |
| 0x0440: kyrgyz_kyrgyzstan | |
| 0x0454: lao_lao | |
| 0x0426: latvian_latvia | |
| 0x0427: lithuanian_lithuania | |
| 0x082E: lower_sorbian_germany | |
| 0x046E: luxembourgish_luxembourg | |
| 0x042F: macedonian_macedonia | |
| 0x083E: malay_brunei_darussalam | |
| 0x043e: malay_malaysia | |
| 0x044C: malayalam_india | |
| 0x043A: maltese_malta | |
| 0x0481: maori_new_zealand | |
| 0x047A: mapudungun_chile | |
| 0x044E: marathi_india | |
| 0x047C: mohawk_mohawk | |
| 0x0450: mongolian_cyrillic_mongolia | |
| 0x0850: mongolian_prc | |
| 0x0461: nepali_nepal | |
| 0x0414: norwegian_bokmal | |
| 0x0814: norwegian_nynorsk | |
| 0x0482: occitan_france | |
| 0x0448: oriya_india | |
| 0x0463: pashto_afghanistan | |
| 0x0429: persian_iran | |
| 0x0415: polish_poland | |
| 0x0416: portuguese_brazilian | |
| 0x0816: portuguese | |
| 0x0867: pular_senegal | |
| 0x0446: punjabi_india | |
| 0x0846: punjabi_pakistan | |
| 0x046B: quechua_bolivia | |
| 0x086B: quechua_ecuador | |
| 0x0C6B: quechua_peru | |
| 0x0418: romanian_romania | |
| 0x0417: romansh_switzerland | |
| 0x0419: russian_russia | |
| 0x0485: sakha_russia | |
| 0x243B: sami_inari_finland | |
| 0x103B: sami_lule_norway | |
| 0x143B: sami_lule_sweden | |
| 0x0C3B: sami_northern_finland | |
| 0x043B: sami_northern_norway | |
| 0x083B: sami_northern_sweden | |
| 0x203B: sami_skolt_finland | |
| 0x183B: sami_southern_norway | |
| 0x1C3B: sami_southern_sweden | |
| 0x044F: sanskrit_india | |
| 0x7C1A: serbian_neutral | |
| 0x1C1A: serbian_bosnia_herzegovina_cyrillic | |
| 0x181A: serbian_bosnia_herzegovina_latin | |
| 0x0C1A: serbian_cyrillic | |
| 0x081A: serbian_latin | |
| 0x046C: sotho_northern_south_africa | |
| 0x0832: tswana_botswana | |
| 0x0432: tswana_south_africa | |
| 0x0459: sindhi_india | |
| 0x0859: sindhi_pakistan | |
| 0x045B: sinhalese_sri_lanka | |
| 0x041B: slovak_slovakia | |
| 0x0424: slovenian_slovenia | |
| 0x2C0A: spanish_argentina | |
| 0x400A: spanish_bolivia | |
| 0x340A: spanish_chile | |
| 0x240A: spanish_colombia | |
| 0x140A: spanish_costa_rica | |
| 0x1C0A: spanish_dominican_republic | |
| 0x300A: spanish_ecuador | |
| 0x440A: spanish_el_salvador | |
| 0x100A: spanish_guatemala | |
| 0x480A: spanish_honduras | |
| 0x080A: spanish_mexican | |
| 0x4C0A: spanish_nicaragua | |
| 0x180A: spanish_panama | |
| 0x3C0A: spanish_paraguay | |
| 0x280A: spanish_peru | |
| 0x500A: spanish_puerto_rico | |
| 0x0C0A: spanish_modern | |
| 0x040A: spanish | |
| 0x540A: spanish_us | |
| 0x380A: spanish_uruguay | |
| 0x200A: spanish_venezuela | |
| 0x0441: swahili | |
| 0x081D: swedish_finland | |
| 0x041D: swedish | |
| 0x041D: swedish_sweden | |
| 0x045A: syriac | |
| 0x0428: tajik_tajikistan | |
| 0x085F: tamazight_algeria_latin | |
| 0x0449: tamil_india | |
| 0x0849: tamil_sri_lanka | |
| 0x0444: tatar_russia | |
| 0x044A: telugu_india | |
| 0x041E: thai_thailand | |
| 0x0451: tibetan_prc | |
| 0x0873: tigrinya_eritrea | |
| 0x0473: tigrinya_ethiopia | |
| 0x0873: tigrigna_eritrea | |
| 0x041F: turkish_turkey | |
| 0x0442: turkmen_turkmenistan | |
| 0x0422: ukrainian_ukraine | |
| 0x042E: upper_sorbian_germany | |
| 0x0820: urdu_india | |
| 0x0420: urdu_pakistan | |
| 0x0480: uighur_prc | |
| 0x0843: uzbek_cyrillic | |
| 0x0443: uzbek_latin | |
| 0x0803: valencian_valencia | |
| 0x042A: vietnamese_vietnam | |
| 0x0452: welsh_united_kingdom | |
| 0x0488: wolof_senegal | |
| 0x0478: yi_prc | |
| 0x046A: yoruba_nigeria | |
| # All other links .. | |
| doc-ref: | | |
| https://en.wikipedia.org/wiki/Amazon_Kindle#File_formats | |
| https://wiki.mobileread.com/wiki/KindleUnpack | |
| https://www.mobileread.com/forums/showthread.php?t=166536&page=3 | |
| https://web.archive.org/web/20140113152714/http://extraordinarycommons.com/creating-kindle-mobi-and-kf8-from-different-sources/ | |
| https://www.mobileread.com/forums/showthread.php?p=1942007#post1942007 | |
| https://www.mobileread.com/forums/showthread.php?t=96903 | |
| https://www.mobileread.com/forums/showthread.php?t=61986 | |
| https://www.mobileread.com/forums/showthread.php?t=171529 | |
| https://wiki.mobileread.com/wiki/AZW | |
| https://wiki.mobileread.com/wiki/AZW1#AZW1 | |
| https://wiki.mobileread.com/wiki/KF8 | |
| https://wiki.mobileread.com/wiki/KFX | |
| https://wiki.mobileread.com/wiki/JXR | |
| https://wiki.mobileread.com/wiki/AZW4 | |
| https://wiki.mobileread.com/wiki/MOBI | |
| https://wiki.mobileread.com/wiki/PalmDOC | |
| http://www.hotpaw.com/rhn/palm/pdb.txt | |
| https://www.epubor.com/difference-between-kindle-content-azw-azw3-prc-mobi-topaz.html | |
| https://teleread.org/2017/01/29/latest-kindle-for-pc-no-longer-uses-calibre-compatible-azw-files/ | |
| https://github.com/kovidgoyal/calibre/tree/master/src/calibre/ebooks/mobi | |
| https://github.com/kroo/mobi-python/blob/master/mobi/__init__.py | |
| https://github.com/sumatrapdfreader/sumatrapdf/blob/master/src/utils/PalmDbReader.h | |
| https://github.com/alphabetum/kindler/blob/master/lib/mobi/header.rb | |
| https://github.com/obra/unsavory-epub-hacks/blob/master/mobiperl/lib/MobiPerl/EXTH.pm | |
| http://search.cpan.org/~azed/EBook-Tools-v0.4.9/lib/EBook/Tools/Mobipocket.pm | |
| https://github.com/pthcode/alexandria/blob/master/mobi.py | |
| https://github.com/pwr/KSP/blob/master/tools/DumpMobiHeader.py | |
| https://github.com/kevinhendricks/KindleUnpack/blob/master/DumpMobiHeader_v022.py | |
| https://github.com/quiris11/ExtractCoverThumbs/blob/master/lib/kindle_unpack.py | |
| http://www.fabiszewski.net/libmobi/index.html | |
| http://www.fabiszewski.net/libmobi/structMOBIMobiHeader.html | |
| http://www.fabiszewski.net/libmobi/mobitool_8c-example.html | |
| https://github.com/kovidgoyal/calibre/blob/master/src/calibre/ebooks/mobi/langcodes.py |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
→ https://github.com/kaitai-io/kaitai_struct_formats