diff --git a/format_docs/pdb/ereader.txt b/format_docs/pdb/ereader.txt index 5770c37e65..d0192d1633 100644 --- a/format_docs/pdb/ereader.txt +++ b/format_docs/pdb/ereader.txt @@ -10,7 +10,7 @@ than Dropbook. Dropbook is a GUI application that only runs on Windows and Apple’s OS X. -PDB Identiy +PDB Identity ------- PNRdPPrs @@ -29,7 +29,7 @@ Record 0, eReader header (202) ------------------ Note all values are in 2 byte increments. Like values are condensed into a -range. The range can be borken into 2 byte sections which represent the actual +range. The range can be broken into 2 byte sections which represent the actual stored values. bytes content comments @@ -48,7 +48,7 @@ bytes content comments 114-116 Garbage 116-202 Unknown -* Garbage: Intentially random values. +* Garbage: Intentionally random values. Text Records (202) @@ -98,7 +98,7 @@ bytes content comments contained in the file 20-22 Number of images The number of images contained in the file 22-24 Number of links The number of links contained in the file -24-26 Metadata avaliable Is there a metadata record in the file? +24-26 Metadata available Is there a metadata record in the file? 0 = None, 1 = There is a metadata record 26-28 Unknown Value of 0 is used 28-30 Number of Footnotes The number of footnote records in the file @@ -286,7 +286,7 @@ E.G. Gibraltar Earth\x00Michael McCollum\x001999\x00Sci Fi Arizona\x001929381255\x00 -The metdata record is always followed by a record which contains 'MeTaInFo\x00' +The metadata record is always followed by a record which contains 'MeTaInFo\x00' Note: Starting with DropBook 1.5.2 'MeTaInFo\x00' is not following Metadata Record. It is a separate record that ends the file and there are some more diff --git a/format_docs/pdb/mbp.txt b/format_docs/pdb/mbp.txt index 13959a6381..7b7753e321 100644 --- a/format_docs/pdb/mbp.txt +++ b/format_docs/pdb/mbp.txt @@ -1,10 +1,10 @@ -// BEGINING OF FILE +// BEGINNING OF FILE // NOTES: // 1* Numeric data stored as big endian, 32 bits. // 2* Data padded to 16 bits limits. (Sometimes to 32 bits limits?) // 3* Text stored seems to be an 8 bit encoding padded to 16 bits // (may be "ISO-8859-1"?, or may be just a local machine character set?) -// 4* I initially used the term "MARK" where I should have used "HIGHLIGTH", +// 4* I initially used the term "MARK" where I should have used "HIGHLIGHT", // bear that in mind (it was a bad name election when I started reversing) <0x 31 bytes = book_title_PAR + 0x00 PAD if (book_title_PAR < 31) > @@ -31,7 +31,7 @@ MOBI // Order of Indexes: from the beginning of this MBP file, // forward to the end of the file. // Nevertheless, see these comments for order relative to: -// "BEGINING OF USER DATA": order of Data marks. +// "BEGINNING OF USER DATA": order of Data marks. // "FINAL GROUP OF MARKS": order of final marks. [for each {NOTE,MARK,CORRECTION,DRAWING,BOOKMARK, AUTHOR,TITLE,CATEGORY,GENRE,ABSTRACT,COVER,PUBLISHER, @@ -95,10 +95,10 @@ BPAR <0x FF FF FF FF> [fi] -// BEGINING OF USER DATA: +// BEGINNING OF USER DATA: // Order of {NOTE,MARK,CORRECTION,DRAWING} : // starts with user data at the end of the file, -// going backwards to the begining of the file: +// going backwards to the beginning of the file: //-------------------------------------------------------------------- [for each {NOTE,MARK,CORRECTION,DRAWING}] //------------------------------- @@ -193,7 +193,7 @@ DATA DATA <0x 4 bytes = size of raw data> ADQM - // NOTE: bakground color is stored in corresponding BKMK. + // NOTE: background color is stored in corresponding BKMK. [begin DRAWING format] ...4 = <0x 00 00 00 01> ??? <0x 4 bytes = X POSITION OF UPPER LEFT CORNER??? > @@ -339,7 +339,7 @@ PUBL // FINAL GROUP OF MARKS // Order of {NOTE,MARK,CORRECTION} : -// starts with user data at the begining of the file, +// starts with user data at the beginning of the file, // going forwards to the end: //-------------------------------------------------------------------- [for each {NOTE,MARK,CORRECTION,DRAWING,BOOKMARK}] diff --git a/format_docs/pdb/mobi.txt b/format_docs/pdb/mobi.txt index 5763866d65..76437ef735 100644 --- a/format_docs/pdb/mobi.txt +++ b/format_docs/pdb/mobi.txt @@ -145,7 +145,7 @@ The following records are only present if the mobi header is long enough. 174 4 DRM Size Number of bytes in DRM info. 176 4 DRM Flags Some flags concerning the DRM info. 180 6 ? -186 2 Last Image record Possible vaule with the last image +186 2 Last Image record Possible value with the last image record. If there are no images in the book this will be 0xffff. 188 4 ? diff --git a/format_docs/pdb/pdb_format.txt b/format_docs/pdb/pdb_format.txt index e6837ac2ad..77fcba87db 100644 --- a/format_docs/pdb/pdb_format.txt +++ b/format_docs/pdb/pdb_format.txt @@ -1,10 +1,10 @@ Format ------ -A PDB file can be borken into multiple parts. The header, record 0 and data. +A PDB file can be broken into multiple parts. The header, record 0 and data. values stored within the various parts are big-endian byte order. The data part is is broken down into multiple sections. The section count and offsets -are referened in the PDB header. Sections can be no more than 65505 bytes in +are referenced in the PDB header. Sections can be no more than 65505 bytes in length. @@ -17,7 +17,7 @@ contained format specific iformation followed by data. DB Header 0 Record 0 . -. Data (borken down into sections) +. Data (broken down into sections) . diff --git a/format_docs/pdb/pml.txt b/format_docs/pdb/pml.txt index b5b357f381..3563e85e52 100644 --- a/format_docs/pdb/pml.txt +++ b/format_docs/pdb/pml.txt @@ -86,7 +86,7 @@ they do. code is decimal XXX. See the PML character table for details. \UXXXX Insert non-ASCII character whose Unicode code - is hexidecimal XXXX. See the Extended PML + is hexadecimal XXXX. See the Extended PML character table for details. \m="imagename.png" Insert the named image. See the section on Images below. @@ -590,7 +590,7 @@ In addition to the special characters supported by earlier versions of eReader (which can be accessed using the \a### tag), all versions of eReader Pro and eReader version 2.4 and later include support for additional special characters and symbols. These symbols can be accessed using the \U#### tag, where #### are -four hexidecimal digits giving the Unicode encoding of the special character. +four hexadecimal digits giving the Unicode encoding of the special character. Only the limited subset of Unicode characters given in the table below are supported. In addition, some of the characters that are included in the table @@ -700,30 +700,30 @@ Spacing Modifier Letters ˘ ˘ \U02D8 BREVE ˙ ˙ \U02D9 DOT ABOVE Greek and Coptic -Α Α \U0391 GREEK CAPTIAL LETTER ALPHA -Β Β \U0392 GREEK CAPTIAL LETTER BETA -Γ Γ \U0393 GREEK CAPTIAL LETTER GAMMA -Δ Ε \U0394 GREEK CAPTIAL LETTER DELTA -Ε Ε \U0395 GREEK CAPTIAL LETTER EPSILON -Ζ Ζ \U0396 GREEK CAPTIAL LETTER ZETA -Η Η \U0397 GREEK CAPTIAL LETTER ETA -Θ Θ \U0398 GREEK CAPTIAL LETTER THETA -Ι Ι \U0399 GREEK CAPTIAL LETTER IOTA -Κ Κ \U039A GREEK CAPTIAL LETTER KAPPA -Λ Λ \U039B GREEK CAPTIAL LETTER LAMBDA -Μ Μ \U039C GREEK CAPTIAL LETTER MU -Ν Ν \U039D GREEK CAPTIAL LETTER NU -Ξ Ξ \U039E GREEK CAPTIAL LETTER XI -Ο Ο \U039F GREEK CAPTIAL LETTER OMICRON -Π Π \U03A0 GREEK CAPTIAL LETTER PI -Ρ Ρ \U03A1 GREEK CAPTIAL LETTER RHO -Σ Σ \U03A3 GREEK CAPTIAL LETTER SIGMA -Τ Τ \U03A4 GREEK CAPTIAL LETTER TAU -Υ Υ \U03A5 GREEK CAPTIAL LETTER UPSILON -Φ Φ \U03A6 GREEK CAPTIAL LETTER PHI -Χ Χ \U03A7 GREEK CAPTIAL LETTER CHI -Ψ Ψ \U03A8 GREEK CAPTIAL LETTER PSI -Ω Ω \U03A9 GREEK CAPTIAL LETTER OMEGA +Α Α \U0391 GREEK CAPITAL LETTER ALPHA +Β Β \U0392 GREEK CAPITAL LETTER BETA +Γ Γ \U0393 GREEK CAPITAL LETTER GAMMA +Δ Ε \U0394 GREEK CAPITAL LETTER DELTA +Ε Ε \U0395 GREEK CAPITAL LETTER EPSILON +Ζ Ζ \U0396 GREEK CAPITAL LETTER ZETA +Η Η \U0397 GREEK CAPITAL LETTER ETA +Θ Θ \U0398 GREEK CAPITAL LETTER THETA +Ι Ι \U0399 GREEK CAPITAL LETTER IOTA +Κ Κ \U039A GREEK CAPITAL LETTER KAPPA +Λ Λ \U039B GREEK CAPITAL LETTER LAMBDA +Μ Μ \U039C GREEK CAPITAL LETTER MU +Ν Ν \U039D GREEK CAPITAL LETTER NU +Ξ Ξ \U039E GREEK CAPITAL LETTER XI +Ο Ο \U039F GREEK CAPITAL LETTER OMICRON +Π Π \U03A0 GREEK CAPITAL LETTER PI +Ρ Ρ \U03A1 GREEK CAPITAL LETTER RHO +Σ Σ \U03A3 GREEK CAPITAL LETTER SIGMA +Τ Τ \U03A4 GREEK CAPITAL LETTER TAU +Υ Υ \U03A5 GREEK CAPITAL LETTER UPSILON +Φ Φ \U03A6 GREEK CAPITAL LETTER PHI +Χ Χ \U03A7 GREEK CAPITAL LETTER CHI +Ψ Ψ \U03A8 GREEK CAPITAL LETTER PSI +Ω Ω \U03A9 GREEK CAPITAL LETTER OMEGA α α \U03B1 GREEK SMALL LETTER ALPHA β β \U03B2 GREEK SMALL LETTER BETA γ γ \U03B3 GREEK SMALL LETTER GAMMA @@ -877,13 +877,13 @@ Private Use Area - \UE019 LATIN SMALL LETTER M WITH MACRON - \UE01A LATIN SMALL LETTER M WITH TILDE - \UE01B LATIN SMALL LETTER O WITH CEDILLA - - \UE01C LATIN SMALL LETTER O WITH MACRON AND CIRUMFLEX + - \UE01C LATIN SMALL LETTER O WITH MACRON AND CIRCUMFLEX - \UE01E LATIN SMALL LIGATURE OI - \UE01F LATIN SMALL LIGATURE OO - \UE020 LATIN SMALL LIGATURE OO WITH MACRON - \UE021 LATIN SMALL LIGATURE OU - \UE022 LATIN SMALL LETTER OPEN O WITH ACUTE - - \UE023 LATIN SMALL LETTER R WITH DIARESIS + - \UE023 LATIN SMALL LETTER R WITH DIAERESIS - \UE024 LATIN SMALL LETTER R WITH CIRCUMFLEX - \UE025 LATIN SMALL LETTER R WITH RING BELOW - \UE026 LATIN SMALL LETTER S WITH VERTICAL LINE ABOVE diff --git a/format_docs/pdb/ztxt.txt b/format_docs/pdb/ztxt.txt index 98fb6bae3e..8fdc6f9068 100644 --- a/format_docs/pdb/ztxt.txt +++ b/format_docs/pdb/ztxt.txt @@ -123,7 +123,7 @@ UInt16 recordSize; recordSize is the size in bytes of a text record. This field is important, as the size of text and decompression buffers is based on this value. It is used by Weasel to navigate though the text so it can map absolute offsets to record -numberss. 8192 is the default. With compression mode 1, this is the amount of +numbers. 8192 is the default. With compression mode 1, this is the amount of data inside each compressed record (except maybe the last one), but the actual compressed records will likely have varying sizes. In mode 2, both compressed records and the resulting text records are all of this size (except, again, the diff --git a/format_docs/rb.txt b/format_docs/rb.txt index 2912f0e9bd..9b329bc949 100644 --- a/format_docs/rb.txt +++ b/format_docs/rb.txt @@ -23,7 +23,7 @@ Details ------- The first 4 bytes of the file seem to be a magic number (in hex): B0 0C -B0 0C. I like to think of this as a hexidecimal pun on the word "book" +B0 0C. I like to think of this as a hexadecimal pun on the word "book" (repeated). [Matt Greenwood has reported seeing a magic number of "B0 0C F0 0D" in another type of ReB-related file -- i.e. "book food".] diff --git a/src/calibre/ebooks/rtf2xml/char_set.py b/src/calibre/ebooks/rtf2xml/char_set.py index 304a0a271f..7ea445cac4 100644 --- a/src/calibre/ebooks/rtf2xml/char_set.py +++ b/src/calibre/ebooks/rtf2xml/char_set.py @@ -15242,7 +15242,7 @@ UPWARDS DOUBLE ARROW:'DD:8657:⇑ RIGHTWARDS DOUBLE ARROW:'DE:8658:⇒ DOWNWARDS DOUBLE ARROW:'DF:8659:⇓ BETWEEN:'E0:8812:≬ -MATHMATICAL LEFT ANGELBRACKET:'E1:10216:⟨ +MATHEMATICAL LEFT ANGELBRACKET:'E1:10216:⟨ REGISTERED SIGN:'E2:174:® COPYRIGHT:'E3:169:© TRADEMARK SYMBOL:'E4:8482:™ @@ -15257,7 +15257,7 @@ LARGE LEFT BRACKET PART1:'EC:0: LARGE LEFT BRACKET PART3:'EE:0: DIVIDES:'EF:8739:∣ -MATHMATICAL RIGHT ANGLE BRACKET:'F1:10217:⟩ +MATHEMATICAL RIGHT ANGLE BRACKET:'F1:10217:⟩ INTEGRAL:'F2:8747:∫ LARGE INTEGRAL PART 1:'F3:0: LARGE INTEGRAL PART 2:'F4:0: @@ -15265,7 +15265,7 @@ LARGE INTEGRAL PART 3:'F5:0: LARGE RIGHT PARENTHESIS PART2:'F7:0: LARGE RIGHT PARENTHESIS PART3:'F8:0: -LARGE RIGHT SQAURE BRACKET PART1:'F9:0: +LARGE RIGHT SQUARE BRACKET PART1:'F9:0: LARGE RIGHT SQUARE BRACKET PART2:'FA:0: LARGE RIGHT SQUARE BRACKETPART3:'FB:0: LARGE RIGHT BRACKET PART1:'FC:0: @@ -16140,7 +16140,7 @@ SNOWFLAKE:T:10052:❄ SHADOWED WHITE LATIN CROSS:U:10014:✞ SHADOWED WHITE LATIN CROSS:V:10014:✞ MY CELTIC CROSS:W:0: -MALTESE CORSS:X:10016:✠ +MALTESE CROSS:X:10016:✠ STAR OF DAVID:Y:10017:✡ STAR AND CRESCENT:Z:9770:☪ MY FOLDER:0:0: @@ -16334,7 +16334,7 @@ UPWARDS DOUBLE ARROW:221:8657:⇑ RIGHTWARDS DOUBLE ARROW:222:8658:⇒ DOWNWARDS DOUBLE ARROW:223:8659:⇓ BETWEEN:224:8812:≬ -MATHMATICAL LEFT ANGELBRACKET:225:10216:⟨ +MATHEMATICAL LEFT ANGELBRACKET:225:10216:⟨ REGISTERED SIGN:226:174:® COPYRIGHT:227:169:© TRADEMARK SYMBOL:228:8482:™ @@ -16349,7 +16349,7 @@ LARGE LEFT BRACKET PART1:236:0: LARGE LEFT BRACKET PART3:238:0: DIVIDES:239:8739:∣ -MATHMATICAL RIGHT ANGLE BRACKET:241:10217:⟩ +MATHEMATICAL RIGHT ANGLE BRACKET:241:10217:⟩ INTEGRAL:242:8747:∫ LARGE INTEGRAL PART 1:243:0: LARGE INTEGRAL PART 2:244:0: @@ -16357,7 +16357,7 @@ LARGE INTEGRAL PART 3:245:0: LARGE RIGHT PARENTHESIS PART2:247:0: LARGE RIGHT PARENTHESIS PART3:248:0: -LARGE RIGHT SQAURE BRACKET PART1:249:0: +LARGE RIGHT SQUARE BRACKET PART1:249:0: LARGE RIGHT SQUARE BRACKET PART2:250:0: LARGE RIGHT SQUARE BRACKETPART3:251:0: LARGE RIGHT BRACKET PART1:252:0: @@ -16519,7 +16519,7 @@ UPWARDS DOUBLE ARROW:221:unknown:⇑ RIGHTWARDS DOUBLE ARROW:222:unknown:⇒ DOWNWARDS DOUBLE ARROW:223:unknown:⇓ BETWEEN:224:unknown:≬ -MATHMATICAL LEFT ANGELBRACKET:225:unknown:⟨ +MATHEMATICAL LEFT ANGELBRACKET:225:unknown:⟨ REGISTERED SIGN:226:unknown:® COPYRIGHT:227:unknown:© N-ARY SUMMATION:229:8721:∑ @@ -16533,7 +16533,7 @@ LARGE LEFT BRACKET PART1:236:unknown: LARGE LEFT BRACKET PART3:238:unknown: DIVIDES:239:8739:∣ -MATHMATICAL RIGHT ANGLE BRACKET:241:unknown:27E9 +MATHEMATICAL RIGHT ANGLE BRACKET:241:unknown:27E9 INTEGRAL:242:unknown:∫ LARGE INTEGRAL PART 1:243:unknown: LARGE INTEGRAL PART 2:244:unknown: @@ -16541,7 +16541,7 @@ LARGE INTEGRAL PART 3:245:unknown: LARGE RIGHT PARENTHESIS PART1:246:unknown: LARGE RIGHT PARENTHESIS PART2:247:unknown: LARGE RIGHT PARENTHESIS PART3:248:unknown: -LARGE RIGHT SQAURE BRACKET PART1:249:unknown: +LARGE RIGHT SQUARE BRACKET PART1:249:unknown: LARGE RIGHT SQUARE BRACKET PART2:250:unknown: LARGE RIGHT SQUARE BRACKETPART3:251:unknown: LARGE RIGHT BRACKET PART1:252:unknown: diff --git a/src/calibre/ebooks/rtf2xml/field_strings.py b/src/calibre/ebooks/rtf2xml/field_strings.py index 314d2ab951..33602d46f7 100644 --- a/src/calibre/ebooks/rtf2xml/field_strings.py +++ b/src/calibre/ebooks/rtf2xml/field_strings.py @@ -139,7 +139,7 @@ class FieldStrings: 'Ordinal' : 'ordinal', 'CardText' : 'cardinal-text', 'OrdText' : 'ordinal-text', - 'Hex' : 'hexidecimal', + 'Hex' : 'hexadecimal', 'DollarText' : 'dollar-text', 'Upper' : 'upper-case', 'Lower' : 'lower-case',