# This is a basic test that checks ^ and $ treat \r\n as a single line # terminator. If ^ and $ only treated \n as a line terminator, then this would # only match 'xyz' at the end of the haystack. [[test]] name = "basic" regex = '(?mR)^[a-z]+$' haystack = "abc\r\ndef\r\nxyz" matches = [[0, 3], [5, 8], [10, 13]] # Tests that a CRLF-aware '^$' assertion does not match between CR and LF. [[test]] name = "start-end-non-empty" regex = '(?mR)^$' haystack = "abc\r\ndef\r\nxyz" matches = [] # Tests that a CRLF-aware '^$' assertion matches the empty string, just like # a non-CRLF-aware '^$' assertion. [[test]] name = "start-end-empty" regex = '(?mR)^$' haystack = "" matches = [[0, 0]] # Tests that a CRLF-aware '^$' assertion matches the empty string preceding # and following a line terminator. [[test]] name = "start-end-before-after" regex = '(?mR)^$' haystack = "\r\n" matches = [[0, 0], [2, 2]] # Tests that a CRLF-aware '^' assertion does not split a line terminator. [[test]] name = "start-no-split" regex = '(?mR)^' haystack = "abc\r\ndef\r\nxyz" matches = [[0, 0], [5, 5], [10, 10]] # Same as above, but with adjacent runs of line terminators. [[test]] name = "start-no-split-adjacent" regex = '(?mR)^' haystack = "\r\n\r\n\r\n" matches = [[0, 0], [2, 2], [4, 4], [6, 6]] # Same as above, but with adjacent runs of just carriage returns. [[test]] name = "start-no-split-adjacent-cr" regex = '(?mR)^' haystack = "\r\r\r" matches = [[0, 0], [1, 1], [2, 2], [3, 3]] # Same as above, but with adjacent runs of just line feeds. [[test]] name = "start-no-split-adjacent-lf" regex = '(?mR)^' haystack = "\n\n\n" matches = [[0, 0], [1, 1], [2, 2], [3, 3]] # Tests that a CRLF-aware '$' assertion does not split a line terminator. [[test]] name = "end-no-split" regex = '(?mR)$' haystack = "abc\r\ndef\r\nxyz" matches = [[3, 3], [8, 8], [13, 13]] # Same as above, but with adjacent runs of line terminators. [[test]] name = "end-no-split-adjacent" regex = '(?mR)$' haystack = "\r\n\r\n\r\n" matches = [[0, 0], [2, 2], [4, 4], [6, 6]] # Same as above, but with adjacent runs of just carriage returns. [[test]] name = "end-no-split-adjacent-cr" regex = '(?mR)$' haystack = "\r\r\r" matches = [[0, 0], [1, 1], [2, 2], [3, 3]] # Same as above, but with adjacent runs of just line feeds. [[test]] name = "end-no-split-adjacent-lf" regex = '(?mR)$' haystack = "\n\n\n" matches = [[0, 0], [1, 1], [2, 2], [3, 3]] # Tests that '.' does not match either \r or \n when CRLF mode is enabled. Note # that this doesn't require multi-line mode to be enabled. [[test]] name = "dot-no-crlf" regex = '(?R).' haystack = "\r\n\r\n\r\n" matches = [] # This is a test that caught a bug in the one-pass DFA where it (amazingly) was # using 'is_end_lf' instead of 'is_end_crlf' here. It was probably a copy & # paste bug. We insert an empty capture group here because it provokes the meta # regex engine to first find a match and then trip over a panic because the # one-pass DFA erroneously says there is no match. [[test]] name = "onepass-wrong-crlf-with-capture" regex = '(?Rm:().$)' haystack = "ZZ\r" matches = [[[1, 2], [1, 1]]] # This is like onepass-wrong-crlf-with-capture above, except it sets up the # test so that it can be run by the one-pass DFA directly. (i.e., Make it # anchored and start the search at the right place.) [[test]] name = "onepass-wrong-crlf-anchored" regex = '(?Rm:.$)' haystack = "ZZ\r" matches = [[1, 2]] anchored = true bounds = [1, 3]