Mercurial > libunicode
changeset 3:d9d3406c1250
New style
| author | David Demelier <markand@malikania.fr> |
|---|---|
| date | Mon, 12 Jun 2017 09:47:46 +0200 |
| parents | 84765c6f4872 |
| children | 34a7a99dbcfa |
| files | generator/cat/cat.cpp generator/make-unicode/src/mkunicode.c generator/make-unicode/unicode-after.cpp generator/make-unicode/unicode.hpp unicode.cpp unicode.hpp |
| diffstat | 6 files changed, 60 insertions(+), 112 deletions(-) [+] |
line wrap: on
line diff
--- a/generator/cat/cat.cpp Thu Feb 02 18:07:27 2017 +0100 +++ b/generator/cat/cat.cpp Mon Jun 12 09:47:46 2017 +0200 @@ -38,9 +38,8 @@ std::ifstream input(argv[i]); std::string line; - while (std::getline(input, line)) { + while (std::getline(input, line)) output << line << "\n"; - } } return 0;
--- a/generator/make-unicode/src/mkunicode.c Thu Feb 02 18:07:27 2017 +0100 +++ b/generator/make-unicode/src/mkunicode.c Mon Jun 12 09:47:46 2017 +0200 @@ -391,27 +391,24 @@ if(isr) fprintf(out, " p = rbsearch(c, is%sr, nelem (is%sr) / 2, 2);\n\n" - " if (p && c >= p[0] && c <= p[1]) {\n" - " return true;\n" - " }\n", + " if (p && c >= p[0] && c <= p[1])\n" + " return true;\n", label, label); if(isp) fprintf(out, "\n" " p = rbsearch(c, is%sp, nelem (is%sp) / 2, 2);\n\n" - " if (p && c >= p[0] && c <= p[1] && !((c - p[0]) & 1)) {\n" - " return true;\n" - " }\n", + " if (p && c >= p[0] && c <= p[1] && !((c - p[0]) & 1))\n" + " return true;\n", label, label); if(iss) fprintf(out, "\n" " p = rbsearch(c, is%ss, nelem (is%ss), 1);\n\n" - " if (p && c == p[0]) {\n" - " return true;\n" - " }\n", + " if (p && c == p[0])\n" + " return true;\n", label, label); @@ -570,27 +567,24 @@ if(tor) fprintf(out, " p = rbsearch(c, to%sr, nelem (to%sr) / 3, 3);\n\n" - " if (p && c >= p[0] && c <= p[1]) {\n" - " return c + p[2] - %d;\n" - " }\n", + " if (p && c >= p[0] && c <= p[1])\n" + " return c + p[2] - %d;\n", label, label, TO_OFFSET); if(top) fprintf(out, "\n" " p = rbsearch(c, to%sp, nelem (to%sp) / 3, 3);\n\n" - " if (p && c >= p[0] && c <= p[1] && !((c - p[0]) & 1)) {\n" - " return c + p[2] - %d;\n" - " }\n", + " if (p && c >= p[0] && c <= p[1] && !((c - p[0]) & 1))\n" + " return c + p[2] - %d;\n", label, label, TO_OFFSET); if(tos) fprintf(out, "\n" " p = rbsearch(c, to%ss, nelem (to%ss) / 2, 2);\n\n" - " if (p && c == p[0]) {\n" - " return c + p[1] - %d;\n" - " }\n\n", + " if (p && c == p[0])\n" + " return c + p[1] - %d;\n\n", label, label, TO_OFFSET); fprintf(out, @@ -611,9 +605,8 @@ " const char32_t* p;\n" "\n" " p = rbsearch(c, is%sr, nelem (is%sr) / 2, 2);\n\n" - " if (p && c >= p[0] && c <= p[1]) {\n" - " return true;\n" - " }\n\n" + " if (p && c >= p[0] && c <= p[1])\n" + " return true;\n\n" " return false;\n" "}\n" "\n", @@ -645,13 +638,11 @@ " if (c >= p[0]) {\n" " t = p;\n" " n = n - m;\n" - " } else {\n" + " } else\n" " n = m;\n" - " }\n" " }\n\n" - " if (n && c >= t[0]) {\n" - " return t;\n" - " }\n\n" + " if (n && c >= t[0])\n" + " return t;\n\n" " return nullptr;\n" "}\n\n" "} // !namespace\n\n"
--- a/generator/make-unicode/unicode-after.cpp Thu Feb 02 18:07:27 2017 +0100 +++ b/generator/make-unicode/unicode-after.cpp Mon Jun 12 09:47:46 2017 +0200 @@ -57,36 +57,28 @@ int nbytes_utf8(char c) noexcept { - if (static_cast<unsigned char>(c) <= 127) { + if (static_cast<unsigned char>(c) <= 127) return 1; - } - if ((c & 0xE0) == 0xC0) { + if ((c & 0xE0) == 0xC0) return 2; - } - if ((c & 0xF0) == 0xE0) { + if ((c & 0xF0) == 0xE0) return 3; - } - if ((c & 0xF8) == 0xF0) { + if ((c & 0xF8) == 0xF0) return 4; - } return -1; } int nbytes_point(char32_t c) noexcept { - if (c <= 0x7F) { + if (c <= 0x7F) return 1; - } - if (c <= 0x7FF) { + if (c <= 0x7FF) return 2; - } - if (c <= 0xFFFF) { + if (c <= 0xFFFF) return 3; - } - if (c <= 0x1FFFFF) { + if (c <= 0x1FFFFF) return 4; - } return -1; } @@ -110,9 +102,8 @@ char tmp[5]; int size = nbytes_point(array[i]); - if (size < 0) { + if (size < 0) throw std::invalid_argument("invalid sequence"); - } encode(array[i], tmp); res.insert(res.length(), tmp);
--- a/generator/make-unicode/unicode.hpp Thu Feb 02 18:07:27 2017 +0100 +++ b/generator/make-unicode/unicode.hpp Mon Jun 12 09:47:46 2017 +0200 @@ -130,9 +130,8 @@ char32_t point = 0; int size = nbytes_utf8(str[i]); - if (size < 0) { + if (size < 0) throw std::invalid_argument("invalid sequence"); - } decode(point, str.data() + i); function(point); @@ -239,9 +238,8 @@ */ inline std::u32string toupper(std::u32string str) { - for (size_t i = 0; i < str.size(); ++i) { + for (size_t i = 0; i < str.size(); ++i) str[i] = toupper(str[i]); - } return str; } @@ -274,9 +272,8 @@ */ inline std::u32string tolower(std::u32string str) { - for (size_t i = 0; i < str.size(); ++i) { + for (size_t i = 0; i < str.size(); ++i) str[i] = tolower(str[i]); - } return str; }
--- a/unicode.cpp Thu Feb 02 18:07:27 2017 +0100 +++ b/unicode.cpp Mon Jun 12 09:47:46 2017 +0200 @@ -41,14 +41,12 @@ if (c >= p[0]) { t = p; n = n - m; - } else { + } else n = m; - } } - if (n && c >= t[0]) { + if (n && c >= t[0]) return t; - } return nullptr; } @@ -79,9 +77,8 @@ p = rbsearch(c, isspacer, nelem (isspacer) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } return false; } @@ -149,9 +146,8 @@ p = rbsearch(c, isdigitr, nelem (isdigitr) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } return false; } @@ -713,15 +709,13 @@ p = rbsearch(c, isalphar, nelem (isalphar) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } p = rbsearch(c, isalphas, nelem (isalphas), 1); - if (p && c == p[0]) { + if (p && c == p[0]) return true; - } return false; } @@ -1373,15 +1367,13 @@ p = rbsearch(c, isupperr, nelem (isupperr) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } p = rbsearch(c, isuppers, nelem (isuppers), 1); - if (p && c == p[0]) { + if (p && c == p[0]) return true; - } return false; } @@ -2033,15 +2025,13 @@ p = rbsearch(c, islowerr, nelem (islowerr) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } p = rbsearch(c, islowers, nelem (islowers), 1); - if (p && c == p[0]) { + if (p && c == p[0]) return true; - } return false; } @@ -2646,15 +2636,13 @@ p = rbsearch(c, istitler, nelem (istitler) / 2, 2); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return true; - } p = rbsearch(c, istitles, nelem (istitles), 1); - if (p && c == p[0]) { + if (p && c == p[0]) return true; - } return false; } @@ -3323,15 +3311,13 @@ p = rbsearch(c, toupperr, nelem (toupperr) / 3, 3); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return c + p[2] - 1048576; - } p = rbsearch(c, touppers, nelem (touppers) / 2, 2); - if (p && c == p[0]) { + if (p && c == p[0]) return c + p[1] - 1048576; - } return c; } @@ -3992,15 +3978,13 @@ p = rbsearch(c, tolowerr, nelem (tolowerr) / 3, 3); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return c + p[2] - 1048576; - } p = rbsearch(c, tolowers, nelem (tolowers) / 2, 2); - if (p && c == p[0]) { + if (p && c == p[0]) return c + p[1] - 1048576; - } return c; } @@ -4669,15 +4653,13 @@ p = rbsearch(c, totitler, nelem (totitler) / 3, 3); - if (p && c >= p[0] && c <= p[1]) { + if (p && c >= p[0] && c <= p[1]) return c + p[2] - 1048576; - } p = rbsearch(c, totitles, nelem (totitles) / 2, 2); - if (p && c == p[0]) { + if (p && c == p[0]) return c + p[1] - 1048576; - } return c; } @@ -4741,36 +4723,28 @@ int nbytes_utf8(char c) noexcept { - if (static_cast<unsigned char>(c) <= 127) { + if (static_cast<unsigned char>(c) <= 127) return 1; - } - if ((c & 0xE0) == 0xC0) { + if ((c & 0xE0) == 0xC0) return 2; - } - if ((c & 0xF0) == 0xE0) { + if ((c & 0xF0) == 0xE0) return 3; - } - if ((c & 0xF8) == 0xF0) { + if ((c & 0xF8) == 0xF0) return 4; - } return -1; } int nbytes_point(char32_t c) noexcept { - if (c <= 0x7F) { + if (c <= 0x7F) return 1; - } - if (c <= 0x7FF) { + if (c <= 0x7FF) return 2; - } - if (c <= 0xFFFF) { + if (c <= 0xFFFF) return 3; - } - if (c <= 0x1FFFFF) { + if (c <= 0x1FFFFF) return 4; - } return -1; } @@ -4794,9 +4768,8 @@ char tmp[5]; int size = nbytes_point(array[i]); - if (size < 0) { + if (size < 0) throw std::invalid_argument("invalid sequence"); - } encode(array[i], tmp); res.insert(res.length(), tmp);
--- a/unicode.hpp Thu Feb 02 18:07:27 2017 +0100 +++ b/unicode.hpp Mon Jun 12 09:47:46 2017 +0200 @@ -130,9 +130,8 @@ char32_t point = 0; int size = nbytes_utf8(str[i]); - if (size < 0) { + if (size < 0) throw std::invalid_argument("invalid sequence"); - } decode(point, str.data() + i); function(point); @@ -239,9 +238,8 @@ */ inline std::u32string toupper(std::u32string str) { - for (size_t i = 0; i < str.size(); ++i) { + for (size_t i = 0; i < str.size(); ++i) str[i] = toupper(str[i]); - } return str; } @@ -274,9 +272,8 @@ */ inline std::u32string tolower(std::u32string str) { - for (size_t i = 0; i < str.size(); ++i) { + for (size_t i = 0; i < str.size(); ++i) str[i] = tolower(str[i]); - } return str; }