Commit cc3e47e0 authored by Jens Getreu's avatar Jens Getreu

let all filter names start with capital

parent 62dfe7de
......@@ -110,7 +110,7 @@ as *GNU strings* replacement.
The integer AF is notated in hexadecimal with prefix `0x...`.
For the most common use-cases, predefined filters can be set:
e.g. alias names like `all-ctrl` or `all-ctrl+wsp` are shorthand
e.g. alias names like `All-Ctrl` or `All-Ctrl+Wsp` are shorthand
terms for ASCII-filters "all codes, but no control-codes" or
"all codes, including white-space, but no control-codes.
See the output of `--list-encodings` for more details
......@@ -240,7 +240,7 @@ as *GNU strings* replacement.
shows all UTF-8-leading-bytes and their codes.
Alternatively, predefined alias names for the most common Unicode-blocks
can be used: e.g.`latin`, `cyrillic`, `greek` and others. See the output of
can be used: e.g.`Latin`, `Cyrillic`, `Greek` and others. See the output of
`--list-encodings` for more predefined filter names.
......@@ -329,15 +329,15 @@ Reduce the number of false positives, when scanning for
UTF-16LE or UTF-16BE encoded strings. In the following example
we search for Cyrillic only:
stringsext -t x -e UTF-16le,,none,cyrillic someimage.raw
stringsext -t x -e UTF-16le,,None,Cyrillic someimage.raw
Search for UTF-16LE encoded Arabic and the digits 0 to 9:
stringsext -t x -e UTF-16le,,0x3f000000000000,arabic someimage.raw
stringsext -t x -e UTF-16le,,0x3f000000000000,Arabic someimage.raw
Search for UTF-8 encoded Syriac and all ASCII, control-codes excluded:
stringsext -t x -e UTF-8,,all-ctrl,0x10000000 someimage.raw
stringsext -t x -e UTF-8,,All-Ctrl,0x10000000 someimage.raw
Combine Little-Endian and Big-Endian scanning:
......
......@@ -163,53 +163,53 @@ pub const UBF_UNCOMMON: u64 = 0x000f_0000_0000_0000;
/// For value see chapter *Codepage layout* in
/// [UTF-8 - Wikipedia](https://en.wikipedia.org/wiki/UTF-8)
pub const UNICODE_BLOCK_FILTER_ALIASSE: [([u8; 12], u64, [u8; 25]); 18] = [
(*b"african ", UBF_AFRICAN, *b"all in U+540..U+800 "),
(*b"African ", UBF_AFRICAN, *b"all in U+540..U+800 "),
(
*b"all-asian ",
*b"All-Asian ",
UBF_ALL & !UBF_INVALID & !UBF_ASIAN,
*b"all, except Asian ",
),
(
*b"all ",
*b"All ",
UBF_ALL & !UBF_INVALID,
*b"all valid multibyte UTF-8",
),
(
*b"arabic ",
*b"Arabic ",
UBF_ARABIC | UBF_SYRIAC,
*b"Arabic+Syriac ",
),
(
*b"armenian ",
*b"Armenian ",
UBF_ARMENIAN,
*b"Armenian ",
),
(*b"asian ", UBF_ASIAN, *b"all in U+3000..U+E000 "),
(*b"cjk ", UBF_CJK, *b"CJK : U+4000..U+A000 "),
(*b"common ", UBF_COMMON, *b"all 2-byte-UFT-8 "),
(*b"Asian ", UBF_ASIAN, *b"all in U+3000..U+E000 "),
(*b"CJK ", UBF_CJK, *b"CJK : U+4000..U+A000 "),
(*b"Common ", UBF_COMMON, *b"all 2-byte-UFT-8 "),
(
*b"cyrillic ",
*b"Cyrillic ",
UBF_CYRILLIC,
*b"Cyrillic ",
),
(
*b"default ",
*b"Default ",
UBF_ALL & !UBF_INVALID,
*b"all valid multibyte UTF-8",
),
(*b"greek ", UBF_GREEK, *b"Greek "),
(*b"hangul ", UBF_HANGUL, *b"Hangul: U+B000..U+E000 "),
(*b"hebrew ", UBF_HEBREW, *b"Hebrew "),
(*b"kana ", UBF_KANA, *b"Kana: U+3000..U+4000 "),
(*b"Greek ", UBF_GREEK, *b"Greek "),
(*b"Hangul ", UBF_HANGUL, *b"Hangul: U+B000..U+E000 "),
(*b"Hebrew ", UBF_HEBREW, *b"Hebrew "),
(*b"Kana ", UBF_KANA, *b"Kana: U+3000..U+4000 "),
(
*b"latin ",
*b"Latin ",
UBF_LATIN | UBF_ACCENTS,
*b"Latin + accents ",
),
(*b"none ", !UBF_ALL, *b"block all multibyte UTF-8"),
(*b"private ", UBF_PUA, *b"private use areas "),
(*b"None ", !UBF_ALL, *b"block all multibyte UTF-8"),
(*b"Private ", UBF_PUA, *b"private use areas "),
(
*b"uncommon ",
*b"Uncommon ",
UBF_UNCOMMON | UBF_PUA,
*b"private + all>=U+10_000 ",
),
......@@ -242,21 +242,21 @@ pub const AF_WHITESPACE: u128 = 0x0000_0000_0000_0000_0000_0001_0000_0200;
pub const AF_DEFAULT: u128 = AF_ALL & !AF_CTRL | AF_WHITESPACE;
pub const ASCII_FILTER_ALIASSE: [([u8; 12], u128, [u8; 25]); 6] = [
(*b"all ", AF_ALL, *b"all ASCII = pass all "),
(*b"All ", AF_ALL, *b"all ASCII = pass all "),
(
*b"all-ctrl ",
*b"All-Ctrl ",
AF_ALL & !AF_CTRL,
*b"all-control ",
),
(
*b"all-ctrl+wsp",
*b"All-Ctrl+Wsp",
AF_ALL & !AF_CTRL | AF_WHITESPACE,
*b"all-control+whitespace ",
),
(*b"default ", AF_DEFAULT, *b"all-control+whitespace "),
(*b"none ", AF_NONE, *b"no ASCII = block all "),
(*b"Default ", AF_DEFAULT, *b"all-control+whitespace "),
(*b"None ", AF_NONE, *b"no ASCII = block all "),
(
*b"wsp ",
*b"Wsp ",
AF_WHITESPACE,
*b"only white-space ",
),
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment