summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/luma/print.c24
-rw-r--r--src/luma/utf8dec.c108
-rw-r--r--src/luma/utf8enc.c64
-rw-r--r--src/main.c36
4 files changed, 152 insertions, 80 deletions
diff --git a/src/luma/print.c b/src/luma/print.c
index 8d8ac1d..a085e8f 100644
--- a/src/luma/print.c
+++ b/src/luma/print.c
@@ -1,7 +1,23 @@
+/*
+ Copyright 2021 Gabriel Jensen
+
+ This file is part of luma.
+
+ luma is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+
+ luma is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+ See the GNU Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License along with luma.
+
+ If not, see <https://www.gnu.org/licenses/>.
+*/
# include <luma/utf8enc.h>
# include <stdarg.h>
# include <stdint.h>
# include <stdio.h>
+# include <stdlib.h>
void luma_print(uint32_t * msg,...) {
va_list args;
va_start(args,msg);
@@ -12,13 +28,17 @@ void luma_print(uint32_t * msg,...) {
}
if(msg[n] == (uint32_t){0xFFFD}) {
size_t chrsz = (size_t){0x0};
- uint8_t const * chr = luma_utf8enc((uint32_t[]){va_arg(args,uint32_t),0x0},&chrsz);
+ uint8_t * chr = NULL;
+ luma_utf8enc((uint32_t[]){va_arg(args,uint32_t),0x0},&chr,&chrsz);
fwrite(chr,0x1,chrsz - (size_t){0x1},stdout);
+ free((void *)chr);
continue;
}
size_t chrsz = (size_t){0x0};
- uint8_t const * chr = luma_utf8enc((uint32_t[]){msg[n],0x0,0x0},&chrsz);
+ uint8_t * chr = NULL;
+ luma_utf8enc((uint32_t[]){msg[n],0x0,0x0},&chr,&chrsz);
fwrite(chr,0x1,chrsz - (size_t){0x1},stdout);
+ free((void *)chr);
}
va_end(args);
}
diff --git a/src/luma/utf8dec.c b/src/luma/utf8dec.c
index f6e29be..e6c302e 100644
--- a/src/luma/utf8dec.c
+++ b/src/luma/utf8dec.c
@@ -1,91 +1,105 @@
+/*
+ Copyright 2021 Gabriel Jensen
+
+ This file is part of luma.
+
+ luma is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+
+ luma is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+ See the GNU Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License along with luma.
+
+ If not, see <https://www.gnu.org/licenses/>.
+*/
# include <luma/utf8dec.h>
# include <stdint.h>
# include <stdio.h>
# include <stdlib.h>
-uint32_t * luma_utf8dec(uint8_t const * str,size_t * outszptr) {
+int luma_utf8dec(uint8_t * utf,uint32_t * * codeps,size_t * outszptr) {
size_t sz = (size_t){0x0};
size_t outsz = (size_t){0x0};
for(size_t n = (size_t){0x0};;n += (size_t){0x1}) { // First pass: get size of input array and determine size of output array.
- uint8_t const utf = str[n];
- if(utf == (uint8_t){0x0}) { // Null-terminator.
+ if(utf[n] == (uint8_t){0x0}) { // Null-terminator.
sz = n;
break;
}
- if(utf >= (uint8_t){0xF0}) { // Four byte.
+ if(utf[n] >= (uint8_t){0xF0}) { // Four byte.
outsz += (size_t){0x4};
n += (size_t){0x3};
continue;
}
- if(utf >= (uint8_t){0xE0}) { // Three bytes.
+ if(utf[n] >= (uint8_t){0xE0}) { // Three bytes.
outsz += (size_t){0x3};
n += (size_t){0x2};
continue;
}
- if(utf >= (uint8_t){0xC0}) { // Two bytes.
+ if(utf[n] >= (uint8_t){0xC0}) { // Two bytes.
outsz += (size_t){0x2};
n += (size_t){0x1};
continue;
}
- if(utf >= (uint8_t){0x80}) { // One byte.
+ if(utf[n] >= (uint8_t){0x80}) { // One byte.
outsz += (size_t){0x1};
continue;
}
// Out of range.
- return NULL;
+ return 0x1;
}
outsz += (size_t){0x1}; // Reserve space for null-terminator.
if(outszptr != NULL) {
*outszptr = outsz;
}
- uint32_t * codeps = malloc(outsz);
- codeps[outsz - (size_t){0x1}] = (uint32_t){0x0}; // Create null-terminator on output array.
+ *codeps = malloc(outsz);
+ (*codeps)[outsz - (size_t){0x1}] = (uint32_t){0x0}; // Create null-terminator on output array.
for(size_t n = (size_t){0x0}, outn = (size_t){0x0};n < sz;n += (size_t){0x1},outn += (size_t){0x1}) { // Second pass: decode UTF-8.
- uint8_t utf = str[n];
- if(utf >= (uint8_t){0xF7}) { // Out of range.
- return NULL;
+ uint8_t chr = utf[n];
+ if(chr >= (uint8_t){0xF7}) { // Out of range.
+ return 0x1;
}
- if(utf >= (uint8_t){0xF0}) { // Four byte.
- uint32_t codep = (uint32_t){(utf ^ 0xF0) << 0x12};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80) << 0xC};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80) << 0x6};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80)};
- codeps[outn] = codep;
+ if(chr >= (uint8_t){0xF0}) { // Four byte.
+ uint32_t codep = (uint32_t){(chr ^ 0xF0) << 0x12};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80) << 0xC};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80) << 0x6};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80)};
+ (*codeps)[outn] = codep;
continue;
}
- if(utf >= (uint8_t){0xE0}) { // Three bytes.
- uint32_t codep = (uint32_t){(utf ^ 0xE0) << 0xC};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80) << 0x6};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80)};
- n += (size_t){0x1};
- codeps[outn] = codep;
+ if(chr >= (uint8_t){0xE0}) { // Three bytes.
+ uint32_t codep = (uint32_t){(chr ^ 0xE0) << 0xC};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80) << 0x6};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80)};
+ n += (size_t){0x1};
+ (*codeps)[outn] = codep;
continue;
}
- if(utf >= (uint8_t){0xC0}) { // Two bytes.
- uint32_t codep = (uint32_t){(utf ^ 0xC0) << 0x6};
- n += (size_t){0x1};
- utf = str[n];
- codep += (uint32_t){(utf ^ 0x80)};
- n += (size_t){0x1};
- codeps[outn] = codep;
+ if(chr >= (uint8_t){0xC0}) { // Two bytes.
+ uint32_t codep = (uint32_t){(chr ^ 0xC0) << 0x6};
+ n += (size_t){0x1};
+ chr = utf[n];
+ codep += (uint32_t){(chr ^ 0x80)};
+ n += (size_t){0x1};
+ (*codeps)[outn] = codep;
continue;
}
- if(utf > (uint8_t){0x7F}) { // One byte.
- uint32_t codep = (uint32_t){utf};
- codeps[outn] = codep;
+ if(chr > (uint8_t){0x7F}) { // One byte.
+ uint32_t codep = (uint32_t){chr};
+ (*codeps)[outn] = codep;
continue;
}
// Out of range.
- return NULL;
+ return 0x1;
}
- return codeps;
+ return 0x0;
}
diff --git a/src/luma/utf8enc.c b/src/luma/utf8enc.c
index 296b56f..3315026 100644
--- a/src/luma/utf8enc.c
+++ b/src/luma/utf8enc.c
@@ -1,8 +1,23 @@
+/*
+ Copyright 2021 Gabriel Jensen
+
+ This file is part of luma.
+
+ luma is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+
+ luma is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+ See the GNU Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License along with luma.
+
+ If not, see <https://www.gnu.org/licenses/>.
+*/
# include <luma/utf8enc.h>
# include <stdint.h>
# include <stdio.h>
# include <stdlib.h>
-uint8_t const * luma_utf8enc(uint32_t * codeps,size_t * outszptr) {
+int luma_utf8enc(uint32_t * codeps,uint8_t * * utf,size_t * outszptr) {
size_t sz = (size_t){0x0}; // Size of input array (bytes).
size_t outsz = (size_t){0x0}; // Size of output array /bytes).
for(size_t n = (size_t){0x0};;n += (size_t){0x1}) { // First pass: get size of input array, and determine size of output array.
@@ -12,7 +27,7 @@ uint8_t const * luma_utf8enc(uint32_t * codeps,size_t * outszptr) {
break;
}
if(codep >= (uint32_t){0x110000}) { // Codepoint out of range.
- return NULL;
+ return 0x1;
}
if(codep >= (uint32_t){0x10000}) { // 4 bytes.
outsz += (size_t){0x4};
@@ -33,36 +48,35 @@ uint8_t const * luma_utf8enc(uint32_t * codeps,size_t * outszptr) {
if(outszptr != NULL) {
*outszptr = outsz;
}
- uint8_t * str = malloc(outsz); // Allocate space for output array.
- str[outsz - (size_t){0x1}] = (uint8_t){0x0}; // Create null-terminator on output array.
+ *utf = malloc(outsz); // Allocate space for output array.
+ (*utf)[outsz - (size_t){0x1}] = (uint8_t){0x0}; // Create null-terminator on output array.
for(size_t n = (size_t){0x0}, outn = (size_t){0x0};n < sz;n += (size_t){0x1},outn += (size_t){0x1}) { // Second pass: encode each codepoint into UTF-8.
- uint32_t codep = codeps[n]; // Current Unicode codepoint.
- if(codep >= 0x10000) { // Four bytes.
- str[outn] = (uint8_t){0xF0 + (codep >> 0x12)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + ((codep >> 0xC) & 0x3F)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + ((codep >> 0x6) & 0x3F)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + (codep & 0x3F)};
+ if(codeps[n] >= 0x10000) { // Four bytes.
+ (*utf)[outn] = (uint8_t){0xF0 + (codeps[n] >> 0x12)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + ((codeps[n] >> 0xC) & 0x3F)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + ((codeps[n] >> 0x6) & 0x3F)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + (codeps[n] & 0x3F)};
continue;
}
- if(codep >= 0x800) { // Three bytes.
- str[outn] = (uint8_t){0xE0 + (codep >> 0xC)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + ((codep >> 0x6) & 0x3F)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + (codep & 0x3F)};
+ if(codeps[n] >= 0x800) { // Three bytes.
+ (*utf)[outn] = (uint8_t){0xE0 + (codeps[n] >> 0xC)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + ((codeps[n] >> 0x6) & 0x3F)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + (codeps[n] & 0x3F)};
continue;
}
- if(codep >= 0x80) { // Two bytes.
- str[outn] = (uint8_t){0xC0 + (codep >> 0x6)};
- outn += (size_t){0x1};
- str[outn] = (uint8_t){0x80 + (codep & 0x3F)};
+ if(codeps[n] >= 0x80) { // Two bytes.
+ (*utf)[outn] = (uint8_t){0xC0 + (codeps[n] >> 0x6)};
+ outn += (size_t){0x1};
+ (*utf)[outn] = (uint8_t){0x80 + (codeps[n] & 0x3F)};
continue;
}
// One byte.
- str[outn] = codep;
+ (*utf)[outn] = codeps[n];
}
- return (uint8_t const *){str};
+ return 0x0;
}
diff --git a/src/main.c b/src/main.c
index e5c7ef6..969bdcd 100644
--- a/src/main.c
+++ b/src/main.c
@@ -1,3 +1,18 @@
+/*
+ Copyright 2021 Gabriel Jensen
+
+ This file is part of luma.
+
+ luma is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+
+ luma is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+ See the GNU Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License along with luma.
+
+ If not, see <https://www.gnu.org/licenses/>.
+*/
# include <locale.h>
# include <luma/arch.h>
# include <luma/print.h>
@@ -15,12 +30,21 @@ int main(void) {
for(size_t i = (size_t){0x0};i < sizeof code / sizeof code[0x0];++i) {
printf("Got code %d.\n",code[i]);
}
- uint8_t const * msg = luma_utf8enc((uint32_t[]){0x00A2,0x2C,0x939,0x2C,0x10348,0x2C,0x20AC,0x2C,0x218A,0x2C,0x1F44B,0x0},NULL);
- printf("Array: %s\n",msg);
- free((void *)msg);
- uint32_t * codeps = luma_utf8dec(luma_utf8enc((uint32_t[]){0x1F44B,0x0},NULL),NULL);
- printf("It is %u.\n",codeps[0x0]);
+ {
+ uint8_t * msg = NULL;
+ luma_utf8enc((uint32_t[]){0x00A2,0x2C,0x939,0x2C,0x10348,0x2C,0x20AC,0x2C,0x218A,0x2C,0x1F44B,0x0},&msg,NULL);
+ printf("Array: %s\n",msg);
+ free((void *){msg});
+ }
+ {
+ uint32_t * codeps = NULL;
+ uint8_t * utf = NULL;
+ luma_utf8enc((uint32_t[]){0x1F44B,0x0},&utf,NULL);
+ luma_utf8dec(utf,&codeps,NULL);
+ free((void *)utf);
+ printf("It is %u.\n",codeps[0x0]);
+ free((void *)codeps);
+ }
luma_print((uint32_t[]){0x48,0x65,0x6C,0x6C,0x6F,0x20,0xFFFD,0x65,0x72,0x65,0x21,0x0},(uint32_t){0xF0});
- free((void *)codeps);
exit(EXIT_SUCCESS);
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-25 05:48:13 +0100