throw early draft of parser into the world

2 files changed, 75 insertions, 0 deletions

diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tests/__init__.py
diff --git a/tests/test_parsing.py b/tests/test_parsing.py
new file mode 100644
index 0000000..91787a6
--- /dev/null
+++ b/tests/test_parsing.py
@@ -0,0 +1,75 @@
+import unittest
+
+from crowbar_reference_compiler import parse_header, parse_implementation, scan
+
+
+class TestParsing(unittest.TestCase):
+    def test_basic(self):
+        print(parse_header(scan("int x();")))
+
+    def test_scdoc_str(self):
+        # adapted from https://git.sr.ht/~sircmpwn/scdoc/tree/master/include/str.h
+        print(parse_header(scan(r"""
+include "stdint.h";
+
+struct str {
+    char *str;
+    typedef size_t len;
+    typedef size_t size;
+};
+
+struct str *str_create();
+void str_free(struct str *str);
+void str_reset(struct str *str);
+int str_append_ch(struct str *str, typedef uint32_t ch);
+""")))
+        # adapted from https://git.sr.ht/~sircmpwn/scdoc/tree/master/src/string.c
+        print(parse_implementation(scan(r"""
+include "stdlib.h";
+include "stdint.h";
+include "str.h";
+include "unicode.h";
+
+int ensure_capacity(struct str *str, typedef size_t len) {
+    if (len + 1 >= str->size) {
+        char *new = realloc(str->str, str->size * 2);
+        if (!new) {
+            return 0;
+        }
+        str->str = new;
+        str->size *= 2;
+    }
+    return 1;
+}
+
+struct str *str_create() {
+    struct str *str = calloc(1, sizeof(struct str));
+    str->str = malloc(16);
+    str->size = 16;
+    str->len = 0;
+    str->str[0] = '\0';
+    return str;
+}
+
+void str_free(struct str *str) {
+    if (!str) {
+        return;
+    }
+    free(str->str);
+    free(str);
+}
+
+int str_append_ch(struct str *str, typedef uint32_t ch) {
+    int size = utf8_chsize(ch);
+    if (size <= 0) {
+        return -1;
+    }
+    if (!ensure_capacity(str, str->len + size)) {
+        return -1;
+    }
+    utf8_encode(&str->str[str->len], ch);
+    str->len += size;
+    str->str[str->len] = '\0';
+    return size;
+}
+""")))