content-parser: random fixes, more tests

2 files changed, 170 insertions, 13 deletions

diff --git a/src/content-parser.c b/src/content-parser.c
index 7781c92..041e96d 100644
--- a/src/content-parser.c
+++ b/src/content-parser.c
@@ -588,9 +588,15 @@ hr:
                         parsed = NULL;
                     }
                     else {
-                        state = CONTENT_PARAGRAPH;
+                        state = CONTENT_PARAGRAPH_END;
                         free(tmp);
                         tmp = NULL;
+                        free(prefix);
+                        prefix = NULL;
+                        b_slist_free_full(lines, free);
+                        lines = NULL;
+                        if (is_last)
+                            goto para;
                         break;
                     }
                     free(tmp);
@@ -634,7 +640,8 @@ hr:
                     break;
                 prefix_len = current - start;
                 state = CONTENT_ORDERED_LIST_START;
-                break;
+                if (c != '\n' && c != '\r' && !is_last)
+                    break;
 
             case CONTENT_ORDERED_LIST_START:
                 if (c == '\n' || c == '\r' || is_last) {
@@ -646,19 +653,25 @@ hr:
                         free(tmp2);
                         tmp2 = NULL;
                         if (b_strv_length(tmpv) != 2) {
-                            state = CONTENT_PARAGRAPH;
-                            goto err_li;
+                            state = CONTENT_PARAGRAPH_END;
+                            b_strv_free(tmpv);
+                            tmpv = NULL;
+                            free(tmp);
+                            tmp = NULL;
+                            b_slist_free_full(lines, free);
+                            lines = NULL;
+                            goto para;
                         }
                         for (unsigned int i = 0; tmpv[0][i] != '\0'; i++) {
                             if (!(tmpv[0][i] >= '0' && tmpv[0][i] <= '9')) {
-                                state = CONTENT_PARAGRAPH;
-                                goto err_li;
-                            }
-                        }
-                        for (unsigned int i = 0; tmpv[1][i] != '\0'; i++) {
-                            if (!(tmpv[1][i] == ' ' || tmpv[1][i] == '\t')) {
-                                state = CONTENT_PARAGRAPH;
-                                goto err_li;
+                                state = CONTENT_PARAGRAPH_END;
+                                b_strv_free(tmpv);
+                                tmpv = NULL;
+                                free(tmp);
+                                tmp = NULL;
+                                b_slist_free_full(lines, free);
+                                lines = NULL;
+                                goto para;
                             }
                         }
                         tmp3 = b_strdup(tmp + prefix_len);
@@ -669,7 +682,6 @@ hr:
                         state = CONTENT_ORDERED_LIST_END;
                         free(parsed);
                         parsed = NULL;
-err_li:
                         b_strv_free(tmpv);
                         tmpv = NULL;
                     }
@@ -707,6 +719,7 @@ err_li:
                     break;
 
             case CONTENT_PARAGRAPH_END:
+para:
                 if (c == '\n' || c == '\r' || is_last) {
                     tmp = b_strndup(src + start, end - start);
                     parsed = blogc_content_parse_inline(tmp);
diff --git a/tests/check_content_parser.c b/tests/check_content_parser.c
index ea8de4b..4f46be8 100644
--- a/tests/check_content_parser.c
+++ b/tests/check_content_parser.c
@@ -378,6 +378,24 @@ test_content_parse_ordered_list(void **state)
         "</ol>\n"
         "<p>fuuuu</p>\n");
     free(html);
+    html = blogc_content_parse(
+        "1.\nasd\n"
+        "2. qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1.\n"
+        "asd</p>\n"
+        "<ol>\n"
+        "<li>qwe</li>\n"
+        "</ol>\n");
+    free(html);
+    html = blogc_content_parse("1.\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<ol>\n"
+        "<li></li>\n"
+        "</ol>\n");
+    free(html);
 }
 
 
@@ -463,6 +481,130 @@ test_content_parse_invalid_horizontal_rule(void **state)
 
 
 void
+test_content_parse_invalid_unordered_list(void **state)
+{
+    // more invalid html
+    char *html = blogc_content_parse(
+        "*  asd\n"
+        "1. qwe");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p><em>  asd\n"
+        "1. qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "*  asd\n"
+        "1. qwe\n"
+        "\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p><em>  asd\n"
+        "1. qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "*  asd\n"
+        "1. qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p><em>  asd\n"
+        "1. qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "* asd\n"
+        "1. qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p><em> asd\n"
+        "1. qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "chunda\n"
+        "\n"
+        "* asd\n"
+        "1. qwe\n"
+        "\n"
+        "poi\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>chunda</p>\n"
+        "<p><em> asd\n"
+        "1. qwe</p>\n"
+        "<p>poi</p>\n");
+    free(html);
+}
+
+
+void
+test_content_parse_invalid_ordered_list(void **state)
+{
+    // more invalid html
+    char *html = blogc_content_parse(
+        "1. asd\n"
+        "*  qwe");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1. asd\n"
+        "<em>  qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "1. asd\n"
+        "*  qwe\n"
+        "\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1. asd\n"
+        "<em>  qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "1. asd\n"
+        "*  qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1. asd\n"
+        "<em>  qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "1. asd\n"
+        "*  qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1. asd\n"
+        "<em>  qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "chunda\n"
+        "\n"
+        "1. asd\n"
+        "*  qwe\n"
+        "\n"
+        "poi\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>chunda</p>\n"
+        "<p>1. asd\n"
+        "<em>  qwe</p>\n"
+        "<p>poi</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "1 asd\n"
+        "* qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>1 asd\n"
+        "<em> qwe</p>\n");
+    free(html);
+    html = blogc_content_parse(
+        "a. asd\n"
+        "2. qwe\n");
+    assert_non_null(html);
+    assert_string_equal(html,
+        "<p>a. asd\n"
+        "2. qwe</p>\n");
+    free(html);
+}
+
+
+void
 test_content_parse_inline(void **state)
 {
     char *html = blogc_content_parse_inline(
@@ -497,6 +639,8 @@ main(void)
         unit_test(test_content_parse_invalid_blockquote),
         unit_test(test_content_parse_invalid_code),
         unit_test(test_content_parse_invalid_horizontal_rule),
+        unit_test(test_content_parse_invalid_unordered_list),
+        unit_test(test_content_parse_invalid_ordered_list),
         unit_test(test_content_parse_inline),
     };
     return run_tests(tests);