Skip to content

Commit 5289bd2

Browse files
committed
Second round of updates from Randy:
* Updated header metadata format * Removed language tables without any overrides * Merged changes to Arabic table
1 parent 0be5ba6 commit 5289bd2

152 files changed

Lines changed: 74527 additions & 75383 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

scriptshifter/tables/data/_bengali_base.yml

Lines changed: 4503 additions & 4501 deletions
Large diffs are not rendered by default.

scriptshifter/tables/data/_ethiopic_base.yml

Lines changed: 917 additions & 915 deletions
Large diffs are not rendered by default.

scriptshifter/tables/data/_gurmukhi_base.yml

Lines changed: 4427 additions & 4425 deletions
Large diffs are not rendered by default.

scriptshifter/tables/data/_ignore_base.yml

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,22 @@
11
---
22
general:
33
name: Common ignore list.
4+
description: List of Latin strings not converted.
5+
version: 1.0.0
6+
date: 2025-12-03
47

58
roman_to_script:
69
ignore:
10+
- "At head of title"
711
- "at head of title"
12+
- "Colophon"
813
- "colophon"
14+
- "Cover title"
915
- "date of publication not identified"
1016
- "place of publication not identified"
1117
- "publisher not identified"
1218
- "and one other"
19+
- "and others"
1320
- "et al."
1421
ignore_ptn:
1522
- "and ([a-z0-9]+ )?others"
Lines changed: 18 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,18 @@
1-
---
2-
general:
3-
name: Abazin (Cyrillic)
4-
parents:
5-
- cyrillic_generic
6-
description: Version 1.0 (2025-11-29) Abazin language in the Cyrillic script
7-
8-
roman_to_script:
9-
map:
10-
"H\u0307": "\u04C0"
11-
"h\u0307": "\u04CF"
12-
13-
script_to_roman:
14-
map:
15-
"\u04C0": "H\u0307"
16-
"\u04CF": "h\u0307"
1+
---
2+
general:
3+
name: Abazin (Cyrillic)
4+
description: Abazin language in the Cyrillic script
5+
version: 1.0.0
6+
date: 2025-11-29
7+
parents:
8+
- cyrillic_generic
9+
10+
roman_to_script:
11+
map:
12+
"H\u0307": "\u04C0"
13+
"h\u0307": "\u04CF"
14+
15+
script_to_roman:
16+
map:
17+
"\u04C0": "H\u0307"
18+
"\u04CF": "h\u0307"
Lines changed: 96 additions & 94 deletions
Original file line numberDiff line numberDiff line change
@@ -1,94 +1,96 @@
1-
---
2-
general:
3-
name: Abkhaz (Cyrillic)
4-
parents:
5-
- cyrillic_generic
6-
description: Version 1.0 (2025-11-29) - Abkhaz in Cyrillic script
7-
8-
roman_to_script:
9-
map:
10-
"T\uFE20S\uFE21\u0307": "\u04B4"
11-
"T\u0361S\u0307": "\u04B4"
12-
"T\uFE20s\uFE21\u0307": "\u04B4"
13-
"T\u0361s\u0307": "\u04B4"
14-
"t\uFE20s\uFE21\u0307": "\u04B5"
15-
"t\u0361s\u0307": "\u04B5"
16-
"T\uFE20\u0307S\uFE21": "\u04B4"
17-
"T\u0361\u0307S": "\u04B4"
18-
"T\uFE20\u0307s\uFE21": "\u04B4"
19-
"T\u0361\u0307s": "\u04B4"
20-
"t\uFE20\u0307s\uFE21": "\u04B5"
21-
"t\u0361\u0307s": "\u04B5"
22-
"T\u0307\uFE20S\uFE21": "\u04B4"
23-
"T\u0307\u0361S": "\u04B4"
24-
"T\u0307\uFE20s\uFE21": "\u04B4"
25-
"T\u0307\u0361s": "\u04B4"
26-
"t\u0307\uFE20s\uFE21": "\u04B5"
27-
"t\u0307\u0361s": "\u04B5"
28-
"C\u0301h\u0301": "\u04BE"
29-
"C\u0301H\u0301": "\u04BE"
30-
"c\u0301h\u0301": "\u04BF"
31-
"C\u0301h": "\u04BC"
32-
"C\u0301H": "\u04BC"
33-
"c\u0301h": "\u04BD"
34-
"C\u0307h": "\u04B6"
35-
"C\u0307H": "\u04B6"
36-
"c\u0307h": "\u04B7"
37-
"D\uFE20Z\uFE21": "\u04E0"
38-
"D\u0361Z": "\u04E0"
39-
"D\uFE20z\uFE21": "\u04E0"
40-
"D\u0361z": "\u04E0"
41-
"d\uFE20z\uFE21": "\u04E1"
42-
"d\u0361z": "\u04E1"
43-
"GH": "\u0494"
44-
"Gh": "\u0494"
45-
"gh": "\u0495"
46-
"H\u0307": "\u04FC"
47-
"h\u0307": "\u04FD"
48-
"Kh": "\u04C3"
49-
"KH": "\u04C3"
50-
"kh": "\u04C4"
51-
"PH": "\u0524"
52-
"Ph": "\u0524"
53-
"ph": "\u0525"
54-
"W\u0307": "\u04D8"
55-
"w\u0307": "\u04D9"
56-
"J": "\u040F"
57-
"j": "\u045F"
58-
"Q": "\u049C"
59-
"q": "\u049D"
60-
"W": "\u04A8"
61-
"w": "\u04A9"
62-
"Z": "\u0417"
63-
"z": "\u0437"
64-
65-
script_to_roman:
66-
map:
67-
"\u040F": "J"
68-
"\u0417": "Z"
69-
"\u0437": "z"
70-
"\u045F": "j"
71-
"\u0494": "GH"
72-
"\u0495": "gh"
73-
"\u049C": "Q"
74-
"\u049D": "q"
75-
"\u04A8": "W"
76-
"\u04A9": "w"
77-
"\u04B4": "T\u0361S\u0307"
78-
"\u04B5": "t\u0361s\u0307"
79-
"\u04B6": "C\u0307h"
80-
"\u04B7": "c\u0307h"
81-
"\u04BC": "C\u0301h"
82-
"\u04BD": "c\u0301h"
83-
"\u04BE": "C\u0301h\u0301"
84-
"\u04BF": "c\u0301h\u0301"
85-
"\u04C3": "Kh"
86-
"\u04C4": "kh"
87-
"\u04D8": "W\u0307"
88-
"\u04D9": "w\u0307"
89-
"\u04E0": "D\u0361Z"
90-
"\u04E1": "d\u0361z"
91-
"\u04FC": "H\u0307"
92-
"\u04FD": "h\u0307"
93-
"\u0524": "Ph"
94-
"\u0525": "ph"
1+
---
2+
general:
3+
name: Abkhaz (Cyrillic)
4+
description: Abkhaz language in Cyrillic script
5+
version: 1.0.0
6+
date: 2025-11-29
7+
parents:
8+
- cyrillic_generic
9+
10+
roman_to_script:
11+
map:
12+
"T\uFE20S\uFE21\u0307": "\u04B4"
13+
"T\u0361S\u0307": "\u04B4"
14+
"T\uFE20s\uFE21\u0307": "\u04B4"
15+
"T\u0361s\u0307": "\u04B4"
16+
"t\uFE20s\uFE21\u0307": "\u04B5"
17+
"t\u0361s\u0307": "\u04B5"
18+
"T\uFE20\u0307S\uFE21": "\u04B4"
19+
"T\u0361\u0307S": "\u04B4"
20+
"T\uFE20\u0307s\uFE21": "\u04B4"
21+
"T\u0361\u0307s": "\u04B4"
22+
"t\uFE20\u0307s\uFE21": "\u04B5"
23+
"t\u0361\u0307s": "\u04B5"
24+
"T\u0307\uFE20S\uFE21": "\u04B4"
25+
"T\u0307\u0361S": "\u04B4"
26+
"T\u0307\uFE20s\uFE21": "\u04B4"
27+
"T\u0307\u0361s": "\u04B4"
28+
"t\u0307\uFE20s\uFE21": "\u04B5"
29+
"t\u0307\u0361s": "\u04B5"
30+
"C\u0301h\u0301": "\u04BE"
31+
"C\u0301H\u0301": "\u04BE"
32+
"c\u0301h\u0301": "\u04BF"
33+
"C\u0301h": "\u04BC"
34+
"C\u0301H": "\u04BC"
35+
"c\u0301h": "\u04BD"
36+
"C\u0307h": "\u04B6"
37+
"C\u0307H": "\u04B6"
38+
"c\u0307h": "\u04B7"
39+
"D\uFE20Z\uFE21": "\u04E0"
40+
"D\u0361Z": "\u04E0"
41+
"D\uFE20z\uFE21": "\u04E0"
42+
"D\u0361z": "\u04E0"
43+
"d\uFE20z\uFE21": "\u04E1"
44+
"d\u0361z": "\u04E1"
45+
"GH": "\u0494"
46+
"Gh": "\u0494"
47+
"gh": "\u0495"
48+
"H\u0307": "\u04FC"
49+
"h\u0307": "\u04FD"
50+
"Kh": "\u04C3"
51+
"KH": "\u04C3"
52+
"kh": "\u04C4"
53+
"PH": "\u0524"
54+
"Ph": "\u0524"
55+
"ph": "\u0525"
56+
"W\u0307": "\u04D8"
57+
"w\u0307": "\u04D9"
58+
"J": "\u040F"
59+
"j": "\u045F"
60+
"Q": "\u049C"
61+
"q": "\u049D"
62+
"W": "\u04A8"
63+
"w": "\u04A9"
64+
"Z": "\u0417"
65+
"z": "\u0437"
66+
67+
script_to_roman:
68+
map:
69+
"\u040F": "J"
70+
"\u0417": "Z"
71+
"\u0437": "z"
72+
"\u045F": "j"
73+
"\u0494": "GH"
74+
"\u0495": "gh"
75+
"\u049C": "Q"
76+
"\u049D": "q"
77+
"\u04A8": "W"
78+
"\u04A9": "w"
79+
"\u04B4": "T\u0361S\u0307"
80+
"\u04B5": "t\u0361s\u0307"
81+
"\u04B6": "C\u0307h"
82+
"\u04B7": "c\u0307h"
83+
"\u04BC": "C\u0301h"
84+
"\u04BD": "c\u0301h"
85+
"\u04BE": "C\u0301h\u0301"
86+
"\u04BF": "c\u0301h\u0301"
87+
"\u04C3": "Kh"
88+
"\u04C4": "kh"
89+
"\u04D8": "W\u0307"
90+
"\u04D9": "w\u0307"
91+
"\u04E0": "D\u0361Z"
92+
"\u04E1": "d\u0361z"
93+
"\u04FC": "H\u0307"
94+
"\u04FD": "h\u0307"
95+
"\u0524": "Ph"
96+
"\u0525": "ph"
Lines changed: 18 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,18 @@
1-
---
2-
general:
3-
name: Adygei (Cyrillic)
4-
parents:
5-
- cyrillic_generic
6-
description: Version 1.0 (2025-11-29) Adygei language in the Cyrillic script
7-
8-
roman_to_script:
9-
map:
10-
"H\u0307": "\u04C0"
11-
"h\u0307": "\u04CF"
12-
13-
script_to_roman:
14-
map:
15-
"\u04C0": "H\u0307"
16-
"\u04CF": "h\u0307"
1+
---
2+
general:
3+
name: Adygei (Cyrillic)
4+
description: Adygei language in the Cyrillic script
5+
version: 1.0.0
6+
date: 2025-11-29
7+
parents:
8+
- cyrillic_generic
9+
10+
roman_to_script:
11+
map:
12+
"H\u0307": "\u04C0"
13+
"h\u0307": "\u04CF"
14+
15+
script_to_roman:
16+
map:
17+
"\u04C0": "H\u0307"
18+
"\u04CF": "h\u0307"
Lines changed: 34 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -1,32 +1,34 @@
1-
---
2-
general:
3-
name: Altai (Cyrillic)
4-
parents:
5-
- cyrillic_generic
6-
description: Version 1.0 (2025-11-29) - Altai language in Cyrillic
7-
8-
roman_to_script:
9-
map:
10-
"N\uFE20G\uFE21": "\u04A4"
11-
"N\u0361G": "\u04A4"
12-
"N\uFE20g\uFE21": "\u04A4"
13-
"N\u0361g": "\u04A4"
14-
"n\uFE20g\uFE21": "\u04A5"
15-
"n\u0361g": "\u04A5"
16-
"D\u0301": "\u0408"
17-
"d\u0301": "\u0458"
18-
"O\u0307": "\u04E6"
19-
"o\u0307": "\u04E7"
20-
"U\u0307": "\u04F0"
21-
"u\u0307": "\u04F1"
22-
23-
script_to_roman:
24-
map:
25-
"\u0408": "D\u0301"
26-
"\u0458": "d\u0301"
27-
"\u04A4": "N\u0361G"
28-
"\u04A5": "n\u0361g"
29-
"\u04E6": "O\u0307"
30-
"\u04E7": "o\u0307"
31-
"\u04F0": "U\u0307"
32-
"\u04F1": "u\u0307"
1+
---
2+
general:
3+
name: Altai (Cyrillic)
4+
description: Altai language in Cyrillic script
5+
version: 1.0.0
6+
date: 2025-11-29
7+
parents:
8+
- cyrillic_generic
9+
10+
roman_to_script:
11+
map:
12+
"N\uFE20G\uFE21": "\u04A4"
13+
"N\u0361G": "\u04A4"
14+
"N\uFE20g\uFE21": "\u04A4"
15+
"N\u0361g": "\u04A4"
16+
"n\uFE20g\uFE21": "\u04A5"
17+
"n\u0361g": "\u04A5"
18+
"D\u0301": "\u0408"
19+
"d\u0301": "\u0458"
20+
"O\u0307": "\u04E6"
21+
"o\u0307": "\u04E7"
22+
"U\u0307": "\u04F0"
23+
"u\u0307": "\u04F1"
24+
25+
script_to_roman:
26+
map:
27+
"\u0408": "D\u0301"
28+
"\u0458": "d\u0301"
29+
"\u04A4": "N\u0361G"
30+
"\u04A5": "n\u0361g"
31+
"\u04E6": "O\u0307"
32+
"\u04E7": "o\u0307"
33+
"\u04F0": "U\u0307"
34+
"\u04F1": "u\u0307"

scriptshifter/tables/data/amharic.yml

Lines changed: 0 additions & 15 deletions
This file was deleted.

0 commit comments

Comments
 (0)