added naive string find function. (#543)

* added naive string find function.

include/aws/common/byte_buf.h

@@ -291,6 +291,18 @@ int aws_byte_cursor_split_on_char_n(
     size_t n,
     struct aws_array_list *AWS_RESTRICT output);
 
+/**
+ * Search for an exact byte match inside a cursor. The first match will be returned. Returns AWS_OP_SUCCESS
+ * on successful match and first_find will be set to the offset in input_str, and length will be the remaining length
+ * from input_str past the returned offset. If the match was not found, AWS_OP_ERR will be returned and
+ * AWS_ERROR_STRING_MATCH_NOT_FOUND will be raised.
+ */
+AWS_COMMON_API
+int aws_byte_cursor_find_exact(
+    const struct aws_byte_cursor *AWS_RESTRICT input_str,
+    const struct aws_byte_cursor *AWS_RESTRICT to_find,
+    struct aws_byte_cursor *first_find);
+
 /**
  *
  * Shrinks a byte cursor from the right for as long as the supplied predicate is true

include/aws/common/error.h

@@ -191,6 +191,7 @@ enum aws_common_error {
     AWS_ERROR_MAX_FDS_EXCEEDED,
     AWS_ERROR_SYS_CALL_FAILURE,
     AWS_ERROR_C_STRING_BUFFER_NOT_NULL_TERMINATED,
+    AWS_ERROR_STRING_MATCH_NOT_FOUND,
 
     AWS_ERROR_END_COMMON_RANGE = 0x03FF
 };

source/byte_buf.c

@@ -257,6 +257,44 @@ int aws_byte_cursor_split_on_char(
     return aws_byte_cursor_split_on_char_n(input_str, split_on, 0, output);
 }
 
+int aws_byte_cursor_find_exact(
+    const struct aws_byte_cursor *AWS_RESTRICT input_str,
+    const struct aws_byte_cursor *AWS_RESTRICT to_find,
+    struct aws_byte_cursor *first_find) {
+    if (to_find->len > input_str->len) {
+        return aws_raise_error(AWS_ERROR_STRING_MATCH_NOT_FOUND);
+    }
+
+    if (to_find->len < 1) {
+        return aws_raise_error(AWS_ERROR_SHORT_BUFFER);
+    }
+
+    struct aws_byte_cursor working_cur = *input_str;
+
+    while (working_cur.len) {
+        uint8_t *first_char_location = memchr(working_cur.ptr, (char)*to_find->ptr, working_cur.len);
+
+        if (!first_char_location) {
+            return aws_raise_error(AWS_ERROR_STRING_MATCH_NOT_FOUND);
+        }
+
+        aws_byte_cursor_advance(&working_cur, first_char_location - working_cur.ptr);
+
+        if (working_cur.len < to_find->len) {
+            return aws_raise_error(AWS_ERROR_STRING_MATCH_NOT_FOUND);
+        }
+
+        if (!memcmp(working_cur.ptr, to_find->ptr, to_find->len)) {
+            *first_find = working_cur;
+            return AWS_OP_SUCCESS;
+        }
+
+        aws_byte_cursor_advance(&working_cur, 1);
+    }
+
+    return aws_raise_error(AWS_ERROR_STRING_MATCH_NOT_FOUND);
+}
+
 int aws_byte_buf_cat(struct aws_byte_buf *dest, size_t number_of_args, ...) {
     AWS_PRECONDITION(aws_byte_buf_is_valid(dest));
 

source/common.c

@@ -224,6 +224,9 @@ static struct aws_error_info errors[] = {
     AWS_DEFINE_ERROR_INFO_COMMON(
         AWS_ERROR_C_STRING_BUFFER_NOT_NULL_TERMINATED,
         "A c-string like buffer was passed but a null terminator was not found within the bounds of the buffer."),
+    AWS_DEFINE_ERROR_INFO_COMMON(
+        AWS_ERROR_STRING_MATCH_NOT_FOUND,
+      "The specified substring was not present in the input string."),
 };
 /* clang-format on */
 

tests/CMakeLists.txt

@@ -240,6 +240,10 @@ add_test_case(test_byte_buf_reset)
 add_test_case(test_byte_cursor_compare_lexical)
 add_test_case(test_byte_cursor_compare_lookup)
 
+add_test_case(test_byte_cursor_find_str)
+add_test_case(test_byte_cursor_find_str_not_found)
+add_test_case(test_byte_cursor_find_str_longer_than_input)
+
 add_test_case(byte_swap_test)
 add_test_case(alignment_test)
 

tests/byte_cursor_find_test.c

@@ -0,0 +1,82 @@
+/*
+ * Copyright 2010-2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License").
+ * You may not use this file except in compliance with the License.
+ * A copy of the License is located at
+ *
+ *  http://aws.amazon.com/apache2.0
+ *
+ * or in the "license" file accompanying this file. This file is distributed
+ * on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+ * express or implied. See the License for the specific language governing
+ * permissions and limitations under the License.
+ */
+
+#include <aws/common/byte_buf.h>
+#include <aws/testing/aws_test_harness.h>
+
+static int s_test_byte_cursor_find_str_fn(struct aws_allocator *allocator, void *ctx) {
+    (void)allocator;
+    (void)ctx;
+
+    const char *string_with_match = "This is a string and we want to find a substring of it.";
+    const char *to_find = "and we want";
+
+    struct aws_byte_cursor string_with_match_cur = aws_byte_cursor_from_c_str(string_with_match);
+    struct aws_byte_cursor to_find_cur = aws_byte_cursor_from_c_str(to_find);
+
+    struct aws_byte_cursor find_res;
+    AWS_ZERO_STRUCT(find_res);
+
+    ASSERT_SUCCESS(aws_byte_cursor_find_exact(&string_with_match_cur, &to_find_cur, &find_res));
+    ASSERT_BIN_ARRAYS_EQUALS(to_find_cur.ptr, to_find_cur.len, find_res.ptr, to_find_cur.len);
+    ASSERT_UINT_EQUALS(string_with_match_cur.len - (find_res.ptr - string_with_match_cur.ptr), find_res.len);
+    ASSERT_PTR_EQUALS(string_with_match_cur.ptr + (find_res.ptr - string_with_match_cur.ptr), find_res.ptr);
+
+    return AWS_OP_SUCCESS;
+}
+
+AWS_TEST_CASE(test_byte_cursor_find_str, s_test_byte_cursor_find_str_fn)
+
+static int s_test_byte_cursor_find_str_not_found_fn(struct aws_allocator *allocator, void *ctx) {
+    (void)allocator;
+    (void)ctx;
+
+    const char *string_with_match = "This is a string and we want to find a substring of it.";
+    const char *to_find = "and we went";
+
+    struct aws_byte_cursor string_with_match_cur = aws_byte_cursor_from_c_str(string_with_match);
+    struct aws_byte_cursor to_find_cur = aws_byte_cursor_from_c_str(to_find);
+
+    struct aws_byte_cursor find_res;
+    AWS_ZERO_STRUCT(find_res);
+
+    ASSERT_ERROR(
+        AWS_ERROR_STRING_MATCH_NOT_FOUND, aws_byte_cursor_find_exact(&string_with_match_cur, &to_find_cur, &find_res));
+
+    return AWS_OP_SUCCESS;
+}
+
+AWS_TEST_CASE(test_byte_cursor_find_str_not_found, s_test_byte_cursor_find_str_not_found_fn)
+
+static int s_test_byte_cursor_find_str_longer_than_input_fn(struct aws_allocator *allocator, void *ctx) {
+    (void)allocator;
+    (void)ctx;
+
+    const char *string_with_match = "This ";
+    const char *to_find = "and we want";
+
+    struct aws_byte_cursor string_with_match_cur = aws_byte_cursor_from_c_str(string_with_match);
+    struct aws_byte_cursor to_find_cur = aws_byte_cursor_from_c_str(to_find);
+
+    struct aws_byte_cursor find_res;
+    AWS_ZERO_STRUCT(find_res);
+
+    ASSERT_ERROR(
+        AWS_ERROR_STRING_MATCH_NOT_FOUND, aws_byte_cursor_find_exact(&string_with_match_cur, &to_find_cur, &find_res));
+
+    return AWS_OP_SUCCESS;
+}
+
+AWS_TEST_CASE(test_byte_cursor_find_str_longer_than_input, s_test_byte_cursor_find_str_longer_than_input_fn)