Fossil SCM
added a few comments
Commit
63313a5f168933ddae7dec33807e8282d77573d7
Parent
6051c441edda958…
1 file changed
+7
-7
+7
-7
| --- src/lookslike.c | ||
| +++ src/lookslike.c | ||
| @@ -143,29 +143,29 @@ | ||
| 143 | 143 | ** the derivatives CESU-8 & WTF-8 (as described in the same |
| 144 | 144 | ** wikipedia article referenced previously). |
| 145 | 145 | */ |
| 146 | 146 | |
| 147 | 147 | /* definitions for various UTF-8 sequence lengths */ |
| 148 | -static const unsigned char us2a[] = { | |
| 148 | +static const unsigned char us2a[] = { /* for lead byte 0xC0 */ | |
| 149 | 149 | 2, 0x80, 0x80 |
| 150 | 150 | }; |
| 151 | -static const unsigned char us2b[] = { | |
| 151 | +static const unsigned char us2b[] = { /* for lead bytes 0xC2-0xDF */ | |
| 152 | 152 | 2, 0x80, 0xBF |
| 153 | 153 | }; |
| 154 | -static const unsigned char us3a[] = { | |
| 154 | +static const unsigned char us3a[] = { /* for lead byte 0xE0 */ | |
| 155 | 155 | 3, 0xA0, 0xBF, 0x80, 0xBF |
| 156 | 156 | }; |
| 157 | -static const unsigned char us3b[] = { | |
| 157 | +static const unsigned char us3b[] = { /* for lead bytes 0xE1-0xEF */ | |
| 158 | 158 | 3, 0x80, 0xBF, 0x80, 0xBF |
| 159 | 159 | }; |
| 160 | -static const unsigned char us4a[] = { | |
| 160 | +static const unsigned char us4a[] = { /* for lead byte 0xF0 */ | |
| 161 | 161 | 4, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 162 | 162 | }; |
| 163 | -static const unsigned char us4b[] = { | |
| 163 | +static const unsigned char us4b[] = { /* for lead bytes 0xF1-0xF3 */ | |
| 164 | 164 | 4, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 165 | 165 | }; |
| 166 | -static const unsigned char us4c[] = { | |
| 166 | +static const unsigned char us4c[] = { /* for lead byte 0xF4 */ | |
| 167 | 167 | 4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF |
| 168 | 168 | }; |
| 169 | 169 | |
| 170 | 170 | /* a table used for quick lookup of the definition that goes with a |
| 171 | 171 | * particular lead byte */ |
| 172 | 172 |
| --- src/lookslike.c | |
| +++ src/lookslike.c | |
| @@ -143,29 +143,29 @@ | |
| 143 | ** the derivatives CESU-8 & WTF-8 (as described in the same |
| 144 | ** wikipedia article referenced previously). |
| 145 | */ |
| 146 | |
| 147 | /* definitions for various UTF-8 sequence lengths */ |
| 148 | static const unsigned char us2a[] = { |
| 149 | 2, 0x80, 0x80 |
| 150 | }; |
| 151 | static const unsigned char us2b[] = { |
| 152 | 2, 0x80, 0xBF |
| 153 | }; |
| 154 | static const unsigned char us3a[] = { |
| 155 | 3, 0xA0, 0xBF, 0x80, 0xBF |
| 156 | }; |
| 157 | static const unsigned char us3b[] = { |
| 158 | 3, 0x80, 0xBF, 0x80, 0xBF |
| 159 | }; |
| 160 | static const unsigned char us4a[] = { |
| 161 | 4, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 162 | }; |
| 163 | static const unsigned char us4b[] = { |
| 164 | 4, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 165 | }; |
| 166 | static const unsigned char us4c[] = { |
| 167 | 4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF |
| 168 | }; |
| 169 | |
| 170 | /* a table used for quick lookup of the definition that goes with a |
| 171 | * particular lead byte */ |
| 172 |
| --- src/lookslike.c | |
| +++ src/lookslike.c | |
| @@ -143,29 +143,29 @@ | |
| 143 | ** the derivatives CESU-8 & WTF-8 (as described in the same |
| 144 | ** wikipedia article referenced previously). |
| 145 | */ |
| 146 | |
| 147 | /* definitions for various UTF-8 sequence lengths */ |
| 148 | static const unsigned char us2a[] = { /* for lead byte 0xC0 */ |
| 149 | 2, 0x80, 0x80 |
| 150 | }; |
| 151 | static const unsigned char us2b[] = { /* for lead bytes 0xC2-0xDF */ |
| 152 | 2, 0x80, 0xBF |
| 153 | }; |
| 154 | static const unsigned char us3a[] = { /* for lead byte 0xE0 */ |
| 155 | 3, 0xA0, 0xBF, 0x80, 0xBF |
| 156 | }; |
| 157 | static const unsigned char us3b[] = { /* for lead bytes 0xE1-0xEF */ |
| 158 | 3, 0x80, 0xBF, 0x80, 0xBF |
| 159 | }; |
| 160 | static const unsigned char us4a[] = { /* for lead byte 0xF0 */ |
| 161 | 4, 0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 162 | }; |
| 163 | static const unsigned char us4b[] = { /* for lead bytes 0xF1-0xF3 */ |
| 164 | 4, 0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF |
| 165 | }; |
| 166 | static const unsigned char us4c[] = { /* for lead byte 0xF4 */ |
| 167 | 4, 0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF |
| 168 | }; |
| 169 | |
| 170 | /* a table used for quick lookup of the definition that goes with a |
| 171 | * particular lead byte */ |
| 172 |