From 9f496c077766172465a065eafba56dd5280021a6 Mon Sep 17 00:00:00 2001 From: Greg Anders Date: Mon, 11 May 2020 19:36:41 -0600 Subject: [PATCH] Add helper functions and docstrings to ascii.zig * Add an upper case variant of `allocLowerString` * Add case-sensitive variants of `eqlIgnoreCase`, `indexOfIgnoreCase`, and `indexOfIgnoreCasePos` * Add and update docstrings on functions --- lib/std/ascii.zig | 71 +++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 66 insertions(+), 5 deletions(-) diff --git a/lib/std/ascii.zig b/lib/std/ascii.zig index 8bd959b46d..37cb1e461c 100644 --- a/lib/std/ascii.zig +++ b/lib/std/ascii.zig @@ -227,6 +227,8 @@ test "ascii character classes" { testing.expect(isSpace(' ')); } +/// Allocates a lower case copy of `ascii_string`. +/// Caller owns returned string and must free with `allocator`. pub fn allocLowerString(allocator: *std.mem.Allocator, ascii_string: []const u8) ![]u8 { const result = try allocator.alloc(u8, ascii_string.len); for (result) |*c, i| { @@ -241,6 +243,23 @@ test "allocLowerString" { std.testing.expect(std.mem.eql(u8, "abcdefghijklmnopqrst0234+💩!", result)); } +/// Allocates an upper case copy of `ascii_string`. +/// Caller owns returned string and must free with `allocator`. +pub fn allocUpperString(allocator: *std.mem.Allocator, ascii_string: []const u8) ![]u8 { + const result = try allocator.alloc(u8, ascii_string.len); + for (result) |*c, i| { + c.* = toUpper(ascii_string[i]); + } + return result; +} + +test "allocUpperString" { + const result = try allocUpperString(std.testing.allocator, "aBcDeFgHiJkLmNOPqrst0234+💩!"); + defer std.testing.allocator.free(result); + std.testing.expect(std.mem.eql(u8, "ABCDEFGHIJKLMNOPQRST0234+💩!", result)); +} + +/// Return `true` if `a` and `b` are equal, case insensitive. pub fn eqlIgnoreCase(a: []const u8, b: []const u8) bool { if (a.len != b.len) return false; for (a) |a_c, i| { @@ -255,20 +274,43 @@ test "eqlIgnoreCase" { std.testing.expect(!eqlIgnoreCase("hElLo!", "helro!")); } -/// Finds `substr` in `container`, starting at `start_index`. -/// TODO boyer-moore algorithm -pub fn indexOfIgnoreCasePos(container: []const u8, start_index: usize, substr: []const u8) ?usize { +/// Return `true` if `a` and `b` are equal, case sensitive. +pub fn eqlMatchCase(a: []const u8, b: []const u8) bool { + if (a.len != b.len) return false; + for (a) |a_c, i| { + if (a_c != b[i]) return false; + } + return true; +} + +test "eqlMatchCase" { + std.testing.expect(!eqlMatchCase("HEl💩Lo!", "hel💩lo!")); + std.testing.expect(eqlMatchCase("Hello! ", "Hello! ")); + std.testing.expect(eqlMatchCase("hElLo!", "hElLo!")); +} + +fn indexOfPos(container: []const u8, start_index: usize, substr: []const u8, comptime case_sensitive: bool) ?usize { if (substr.len > container.len) return null; var i: usize = start_index; const end = container.len - substr.len; while (i <= end) : (i += 1) { - if (eqlIgnoreCase(container[i .. i + substr.len], substr)) return i; + if (case_sensitive) { + if (eqlMatchCase(container[i .. i + substr.len], substr)) return i; + } else { + if (eqlIgnoreCase(container[i .. i + substr.len], substr)) return i; + } } return null; } -/// Finds `substr` in `container`, starting at `start_index`. +/// Finds `substr` in `container`, case insensitive, starting at `start_index`. +/// TODO boyer-moore algorithm +pub fn indexOfIgnoreCasePos(container: []const u8, start_index: usize, substr: []const u8) ?usize { + return indexOfPos(container, start_index, substr, false); +} + +/// Finds `substr` in `container`, case insensitive, starting at index 0. pub fn indexOfIgnoreCase(container: []const u8, substr: []const u8) ?usize { return indexOfIgnoreCasePos(container, 0, substr); } @@ -281,3 +323,22 @@ test "indexOfIgnoreCase" { std.testing.expect(indexOfIgnoreCase("FOO foo", "fOo").? == 0); } + +/// Finds `substr` in `container`, case sensitive, starting at `start_index`. +pub fn indexOfMatchCasePos(container: []const u8, start_index: usize, substr: []const u8) ?usize { + return indexOfPos(container, start_index, substr, true); +} + +/// Finds `substr` in `container`, case sensitive, starting at index 0. +pub fn indexOfMatchCase(container: []const u8, substr: []const u8) ?usize { + return indexOfMatchCasePos(container, 0, substr); +} + +test "indexOfMatchCase" { + std.testing.expect(indexOfMatchCase("one Two Three Four", "Four").? == 14); + std.testing.expect(indexOfMatchCase("one two three FouR", "fOur") == null); + std.testing.expect(indexOfMatchCase("foO", "foO").? == 0); + std.testing.expect(indexOfMatchCase("foo", "fool") == null); + + std.testing.expect(indexOfMatchCase("FOO foo", "FOO").? == 0); +}