diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/utf8tabs.inc | 20 | ||||
| -rw-r--r-- | src/utf8tabs.py | 44 |
2 files changed, 32 insertions, 32 deletions
diff --git a/src/utf8tabs.inc b/src/utf8tabs.inc index e893fade..28f30978 100644 --- a/src/utf8tabs.inc +++ b/src/utf8tabs.inc @@ -225,25 +225,25 @@ static struct CaseMapping casemappings[] = { enum { casefold_len = 192 }; -static uint8_t upcase_ind[162] = { +static uint8_t upcase_ind[164] = { 0, 2, 3, 4, 192, 5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 43, 45, 193, 47, 48, 194, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 65, 66, 67, 68, 69, 70, 71, 72, 73, 75, 80, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 195, 196, 109, 110, 111, 113, 114, 115, 116, 117, 118, 119, - 120, 121, 125, 126, 129, 131, 132, 133, 134, 135, 136, 137, 139, 140, 141, 142, 144, 146, 147, 148, - 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, - 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, - 189, 191, + 120, 121, 125, 126, 129, 131, 132, 133, 134, 135, 136, 137, 139, 140, 141, 142, 143, 144, 145, 146, + 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, + 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, + 187, 188, 189, 191, }; static uint8_t lowcase_ind[186] = { 0, 197, 113, 2, 3, 8, 4, 198, 5, 6, 7, 9, 199, 60, 12, 14, 16, 20, 50, 25, - 57, 53, 29, 31, 33, 35, 37, 39, 40, 51, 41, 43, 45, 17, 47, 48, 52, 54, 56, 158, - 59, 63, 154, 152, 155, 11, 13, 15, 18, 19, 174, 21, 175, 22, 170, 173, 24, 23, 177, 148, - 176, 26, 153, 27, 28, 150, 30, 184, 32, 179, 34, 61, 36, 62, 38, 180, 178, 65, 66, 88, - 68, 69, 72, 200, 73, 70, 71, 201, 202, 203, 204, 75, 80, 205, 206, 86, 67, 207, 85, 87, - 90, 89, 91, 92, 94, 93, 95, 96, 109, 110, 190, 100, 196, 208, 209, 210, 211, 212, 213, 214, + 57, 53, 29, 31, 33, 35, 37, 39, 40, 51, 41, 43, 45, 193, 17, 47, 48, 194, 52, 54, + 56, 158, 59, 63, 154, 152, 155, 11, 13, 15, 18, 19, 174, 21, 175, 22, 170, 173, 24, 23, + 177, 148, 176, 26, 153, 27, 28, 150, 30, 184, 32, 179, 34, 61, 36, 62, 38, 180, 178, 65, + 66, 88, 68, 69, 72, 200, 73, 70, 71, 201, 202, 203, 204, 75, 80, 205, 206, 86, 67, 207, + 85, 87, 90, 89, 91, 92, 94, 93, 95, 96, 109, 110, 196, 208, 209, 210, 211, 212, 213, 214, 215, 167, 149, 185, 111, 216, 114, 115, 116, 117, 118, 119, 120, 121, 126, 129, 132, 136, 134, 137, 122, 123, 124, 125, 127, 217, 130, 131, 133, 135, 138, 142, 143, 144, 145, 146, 147, 55, 58, 151, 156, 157, 159, 160, 161, 97, 98, 99, 162, 163, 164, 165, 166, 168, 169, 171, 183, 172, 182, 186, diff --git a/src/utf8tabs.py b/src/utf8tabs.py index f303795c..dfaec055 100644 --- a/src/utf8tabs.py +++ b/src/utf8tabs.py @@ -120,41 +120,41 @@ def main(): casefolding_len = len(casemappings) - # additional Lu => Ll mappings from UnicodeData.txt + # add additional Lu => Ll mappings from UnicodeData.txt + # create upcase_ind: lower => upper index list sorted by mapped lowercase values: + upcase_ind = [] for v in upcase: - if v not in casemappings: + try: + upcase_ind.append(casemappings.index(v)) + except: + upcase_ind.append(len(casemappings)) casemappings.append(v) - # additional Ll => Lu mappings from UnicodeData.txt + # add additional Ll => Lu mappings from UnicodeData.txt + # create lowcase_ind: upper => lower index list sorted by uppercase values: + lowcase_ind = [] for u in lowcase: v = (u[2] - (u[1] - u[0]), u[2], u[1], '') - if not any(x[0]==v[0] and x[1]==v[1] and x[2]==v[2] for x in casemappings): + try: + j = next(i for i,x in enumerate(casemappings) if x[0]==v[0] and x[1]==v[1] and x[2]==v[2]) + lowcase_ind.append(j) + except: + lowcase_ind.append(len(casemappings)) casemappings.append(v) print_table('casemappings', casemappings, style=1) print('enum { casefold_len = %d };' % casefolding_len) - # upper => lower index list sorted by uppercase values: - upcase_ind = [] - for v in upcase: - upcase_ind.append(casemappings.index(v)) + # add "missing" mappings: + for c in ('Ⅰ', 'Ⓐ'): + upcase_ind.append(next(i for i,x in enumerate(casemappings) if x[0]==ord(c))) + for c in ('ẞ', 'Ⅰ', 'Ⓐ'): + lowcase_ind.append(next(i for i,x in enumerate(casemappings) if x[0]==ord(c))) + upcase_ind.sort(key=lambda i: casemappings[i][0]) print_index_table('upcase_ind', upcase_ind) - # lower => upper index list sorted by mapped lowercase values: - lowcase_ind = [i for i in range(len(casemappings))] - lowcase_ind.sort(key=lambda i: casemappings[i][2] - (casemappings[i][1] - casemappings[i][0])) - # remove redundant mappings from lower to upper - for i in range(len(lowcase_ind) - 1, 0, -1): - c1 = casemappings[lowcase_ind[i]] - v = c1[2] - (c1[1] - c1[0]) - for j in range(i): - c2 = casemappings[lowcase_ind[j]] - r1 = c2[2] - (c2[1] - c2[0]) - r2 = c2[2] - if r1 <= v <= r2: - del lowcase_ind[i] - break + lowcase_ind.sort(key=lambda i: casemappings[i][2] - (casemappings[i][1] - casemappings[i][0])) print_index_table('lowcase_ind', lowcase_ind) |