Move unicode module to separate library lib8

9 files changed, 30 insertions, 151 deletions

diff --git a/.gitmodules b/.gitmodules
index d493dd7..a984125 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,3 +1,6 @@
 [submodule "deps/munit"]
 	path = deps/munit
 	url = https://github.com/nemequ/munit.git
+[submodule "deps/libf8"]
+	path = deps/libf8
+	url = git@github.com:Oxore/libf8.git
diff --git a/Makefile b/Makefile
index 967c46c..2a21d7d 100644
--- a/Makefile
+++ b/Makefile
@@ -4,6 +4,7 @@ QQ=@
 TARGET_TETRIS:=tetris
 TARGET_TEST:=test
 MUNIT:=deps/munit
+LIBF8:=deps/libf8
 
 ifeq ($(wildcard $(MUNIT)/*),)
 NOTEST=1
@@ -21,6 +22,7 @@ INCLUDE+=$(PREFIX)/include
 endif
 INCLUDE+=include
 INCLUDE+=$(MUNIT)
+INCLUDE+=$(LIBF8)
 INCLUDE:=$(INCLUDE:%=-I%)
 
 #COMMON+=-fsanitize=address
@@ -46,6 +48,8 @@ endif
 LDFLAGS+=$(COMMON)
 
 LDFLAGS_TETRIS+=$(LDFLAGS)
+LDFLAGS_TETRIS+=-L$(LIBF8)
+LDFLAGS_TETRIS+=-l:libf8.a
 LDFLAGS_TETRIS+=-lcsfml-graphics
 LDFLAGS_TETRIS+=-lcsfml-window
 LDFLAGS_TETRIS+=-lcsfml-system
@@ -62,11 +66,11 @@ ifndef NOTEST
 all: $(TARGET_TEST)
 endif
 
-$(TARGET_TETRIS): $(OBJECTS) $(TARGET)/$(TARGET_TETRIS).c.o
+$(TARGET_TETRIS): $(OBJECTS) $(TARGET)/$(TARGET_TETRIS).c.o $(LIBF8)/libf8.a
 	$(QQ) echo "  LD      $@"
 	$(Q) $(CC) -o $@ $^ $(LDFLAGS_TETRIS)
 
-$(TARGET_TEST): $(TARGET)/$(TARGET_TEST).c.o $(MUNIT)/munit.c.o $(BUILD)/unicode.c.o
+$(TARGET_TEST): $(TARGET)/$(TARGET_TEST).c.o $(MUNIT)/munit.c.o
 	$(QQ) echo "  LD      $@"
 	$(Q) $(CC) -o $@ $^ $(LDFLAGS_TEST)
 
@@ -79,6 +83,9 @@ $(BUILD):
 $(TARGET):
 	$(Q) mkdir -p $@
 
+$(LIBF8)/libf8.a: $(LIBF8)
+	make -C $<
+
 $(MUNIT)/munit.c.o: $(MUNIT)/munit.c
 	$(QQ) echo "  CC      $@"
 	$(Q) $(CC) -c $(CFLAGS) -o $@ $<
diff --git a/README.md b/README.md
index ff88898..57e1ee6 100644
--- a/README.md
+++ b/README.md
@@ -10,9 +10,11 @@ This is unfinished tetris project written in pure C with CSFML library. It is un
 
 __Dependencies__
 
-`SFML`
-`CSFML`
-`libyaml`
+- `SFML` - Graphics and controls
+- `CSFML` - C SFML bindings
+- `libyaml` - YAML parser
+- [`munit`](https://github.com/nemequ/munit) - Testing framework (submodule)
+- [`libf8`](https://github.com/Oxore/libf8) - Unicode helper functions (submodule)
 
 __Compilation and use__
 
diff --git a/deps/libf8 b/deps/libf8
new file mode 160000
+Subproject 599a11a1627c8369b43b462a505030936575ede
diff --git a/include/unicode.h b/include/unicode.h
deleted file mode 100644
index 4e5910a..0000000
--- a/include/unicode.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * unicode.h
- *
- * Unicode - module with some helper unicode functions.
- *
- * SFML uses UTF32 encoding for texts and there is no need to use any full
- * featured library just for a couple of encoding conversion functions.
- *
- * */
-
-size_t  utf8_strlen(char *string);
-void    utf8to32_strcpy(wchar_t *dest, char *src);
diff --git a/src/engine.c b/src/engine.c
index 2a5755b..bad04f5 100644
--- a/src/engine.c
+++ b/src/engine.c
@@ -25,6 +25,7 @@
  *
  * */
 
+#include <f8.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -38,7 +39,6 @@
 #include "vector.h"
 #include "text.h"
 #include "field.h"
-#include "unicode.h"
 #include "painter.h"
 #include "engine.h"
 
diff --git a/src/target/test.c b/src/target/test.c
index b807b92..a92642a 100644
--- a/src/target/test.c
+++ b/src/target/test.c
@@ -1,79 +1,20 @@
 #include "munit.h"
 
-#include "unicode.h"
-
-struct u_pair {
-    char    *utf8;
-    wchar_t *utf32;
-};
-
-struct u_pair text_fixture[] = {
-    {
-        .utf8  =  "Single byte ascii symbols string",
-        .utf32 = L"Single byte ascii symbols string"
-    },
-    {
-        .utf8  =  "\u041A\u0438\u0440\u0438\u043B\u043B\u0438\u0446\u0430",
-        .utf32 = L"\u041A\u0438\u0440\u0438\u043B\u043B\u0438\u0446\u0430"
-    },
-    {
-        .utf8  =  "\u0814\u0820\u080C\u081D\u0813\u0829\u0809\u080C",
-        .utf32 = L"\u0814\u0820\u080C\u081D\u0813\u0829\u0809\u080C"
-    },
-    {
-        .utf8  =  "𓁹",
-        .utf32 = L"𓁹"
-    }
-};
-
-
-static void *test_utf8_strlen_setup(const MunitParameter params[],
-        void *user_data)
-{
-    (void) params;
-    (void) user_data;
-
-    return text_fixture;
-}
-
-static MunitResult test_utf8_strlen(const MunitParameter params[],
-        void *fixture)
+static void *test_dummy_setup(
+        const MunitParameter    params[],
+        void                   *user_data)
 {
     (void) params;
-    struct u_pair *f = fixture;
 
-    for (int i = 0; i < 4; i++)
-        munit_assert_ulong(utf8_strlen(f[i].utf8) * (i + 1),
-                ==, strlen(f[i].utf8));
-
-    return MUNIT_OK;
-}
-
-static void *test_utf8to32_strcpy_setup(const MunitParameter params[],
-        void *user_data)
-{
-    (void) params;
-    (void) user_data;
-
-    return text_fixture;
+    return user_data;
 }
 
-static MunitResult test_utf8to32_strcpy(const MunitParameter params[],
-        void *fixture)
+static MunitResult test_dummy(
+        const MunitParameter    params[],
+        void                   *fixture)
 {
     (void) params;
-
-    struct u_pair  *f = fixture;
-    size_t          len;
-    wchar_t        *str;
-
-    for (int i = 0; i < 4; i++) {
-        len = utf8_strlen(f[i].utf8);
-        str = malloc((len + 1) * sizeof(wchar_t));
-        utf8to32_strcpy(str, f[i].utf8);
-        munit_assert_uint(memcmp(str, f[i].utf32, len), ==, 0);
-        free(str);
-    }
+    (void) fixture;
 
     return MUNIT_OK;
 }
@@ -82,17 +23,9 @@ static const MunitSuite test_suite = {
     "unit",
     (MunitTest[]){
         {
-            "/unicode/utf8_strlen",
-            test_utf8_strlen,
-            test_utf8_strlen_setup,
-            NULL,
-            MUNIT_TEST_OPTION_NONE,
-            NULL
-        },
-        {
-            "/unicode/utf8to32_strcpy",
-            test_utf8to32_strcpy,
-            test_utf8to32_strcpy_setup,
+            "/dummy/dummy",
+            test_dummy,
+            test_dummy_setup,
             NULL,
             MUNIT_TEST_OPTION_NONE,
             NULL
diff --git a/src/text.c b/src/text.c
index 3b361dd..9bace21 100644
--- a/src/text.c
+++ b/src/text.c
@@ -1,3 +1,4 @@
+#include <f8.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -6,7 +7,6 @@
 #include "idlist.h"
 #include "vector.h"
 #include "text.h"
-#include "unicode.h"
 
 static FILE *openFile(char *filename)
 {
diff --git a/src/unicode.c b/src/unicode.c
deleted file mode 100644
index de25ffb..0000000
--- a/src/unicode.c
+++ /dev/null
@@ -1,54 +0,0 @@
-#include <stdlib.h>
-#include <string.h>
-
-#include "unicode.h"
-
-static inline size_t utf8_char_len(unsigned char c)
-{
-    if (c > 0x00 && c < 0xC0)
-        return 1;
-    else if (c >= 0xC2 && c < 0xE0)
-        return 2;
-    else if (c >= 0xE0 && c < 0xF0)
-        return 3;
-    else if (c >= 0xF0 && c < 0xF5)
-        return 4;
-    else
-        return 0;
-}
-
-size_t utf8_strlen(char *string)
-{
-    size_t len = 0, keep = 0;
-    for (char *c = string; *c; (keep ? --keep : ++len), ++c)
-        if (!keep)
-            keep = (keep = utf8_char_len(*c)) ? keep - 1 : keep;
-    return len;
-}
-
-void utf8to32_strcpy(wchar_t *dest, char *src)
-{
-    wchar_t *dc = dest;
-    char *c = src;
-    size_t len = 0;
-    while (*c) {
-        int clen = utf8_char_len(*c);
-        if (clen == 1) {
-            dc[len] = c[0] & 0x7f;
-        } else if (clen == 2) {
-            dc[len] = ((c[0] & 0x1f) << 6) | ((c[1] & 0x3f) << 0);
-        } else if (clen == 3) {
-            dc[len] = ((c[0] & 0x0f) << 12) | ((c[1] & 0x3f) << 6)
-                | ((c[2] & 0x3f) << 0);
-        } else if (clen == 4) {
-            dc[len] = ((c[0] & 0x07) << 18) | ((c[1] & 0x3f) << 12)
-                | ((c[2] & 0x3f) << 6) | ((c[3] & 0x3f) << 0);
-        } else {
-            dc[len] = 0;
-            return;
-        }
-        c += clen;
-        ++len;
-    }
-    dc[len] = 0;
-}