lavf/url: add ff_url_decompose().

(cherry picked from commit d853293679f93ef882e6a5f1c47eb5a65ceddf3d)

4 files changed, 191 insertions, 0 deletions

diff --git a/libavformat/tests/url.c b/libavformat/tests/url.c
index 1d961a1b43..e7d259ab7d 100644
--- a/libavformat/tests/url.c
+++ b/libavformat/tests/url.c
@@ -21,6 +21,31 @@
 #include "libavformat/url.h"
 #include "libavformat/avformat.h"
 
+static void test_decompose(const char *url)
+{
+    URLComponents uc;
+    int len, ret;
+
+    printf("%s =>\n", url);
+    ret = ff_url_decompose(&uc, url, NULL);
+    if (ret < 0) {
+        printf("  error: %s\n", av_err2str(ret));
+        return;
+    }
+#define PRINT_COMPONENT(comp) \
+    len = uc.url_component_end_##comp - uc.comp; \
+    if (len) printf("  "#comp": %.*s\n", len, uc.comp);
+    PRINT_COMPONENT(scheme);
+    PRINT_COMPONENT(authority);
+    PRINT_COMPONENT(userinfo);
+    PRINT_COMPONENT(host);
+    PRINT_COMPONENT(port);
+    PRINT_COMPONENT(path);
+    PRINT_COMPONENT(query);
+    PRINT_COMPONENT(fragment);
+    printf("\n");
+}
+
 static void test(const char *base, const char *rel)
 {
     char buf[200], buf2[200];
@@ -51,6 +76,15 @@ static void test2(const char *url)
 
 int main(void)
 {
+    printf("Testing ff_url_decompose:\n\n");
+    test_decompose("http://user:pass@ffmpeg:8080/dir/file?query#fragment");
+    test_decompose("http://ffmpeg/dir/file");
+    test_decompose("file:///dev/null");
+    test_decompose("file:/dev/null");
+    test_decompose("http://[::1]/dev/null");
+    test_decompose("http://[::1]:8080/dev/null");
+    test_decompose("//ffmpeg/dev/null");
+
     printf("Testing ff_make_absolute_url:\n");
     test(NULL, "baz");
     test("/foo/bar", "baz");
diff --git a/libavformat/url.c b/libavformat/url.c
index 20463a6674..b92409f6b2 100644
--- a/libavformat/url.c
+++ b/libavformat/url.c
@@ -27,6 +27,7 @@
 #if CONFIG_NETWORK
 #include "network.h"
 #endif
+#include "libavutil/avassert.h"
 #include "libavutil/avstring.h"
 
 /**
@@ -78,6 +79,76 @@ int ff_url_join(char *str, int size, const char *proto,
     return strlen(str);
 }
 
+static const char *find_delim(const char *delim, const char *cur, const char *end)
+{
+    while (cur < end && !strchr(delim, *cur))
+        cur++;
+    return cur;
+}
+
+int ff_url_decompose(URLComponents *uc, const char *url, const char *end)
+{
+    const char *cur, *aend, *p;
+
+    av_assert0(url);
+    if (!end)
+        end = url + strlen(url);
+    cur = uc->url = url;
+
+    /* scheme */
+    uc->scheme = cur;
+    p = find_delim(":/", cur, end); /* lavf "schemes" can contain options */
+    if (*p == ':')
+        cur = p + 1;
+
+    /* authority */
+    uc->authority = cur;
+    if (end - cur >= 2 && cur[0] == '/' && cur[1] == '/') {
+        cur += 2;
+        aend = find_delim("/?#", cur, end);
+
+        /* userinfo */
+        uc->userinfo = cur;
+        p = find_delim("@", cur, aend);
+        if (*p == '@')
+            cur = p + 1;
+
+        /* host */
+        uc->host = cur;
+        if (*cur == '[') { /* hello IPv6, thanks for using colons! */
+            p = find_delim("]", cur, aend);
+            if (*p != ']')
+                return AVERROR(EINVAL);
+            if (p + 1 < aend && p[1] != ':')
+                return AVERROR(EINVAL);
+            cur = p + 1;
+        } else {
+            cur = find_delim(":", cur, aend);
+        }
+
+        /* port */
+        uc->port = cur;
+        cur = aend;
+    } else {
+        uc->userinfo = uc->host = uc->port = cur;
+    }
+
+    /* path */
+    uc->path = cur;
+    cur = find_delim("?#", cur, end);
+
+    /* query */
+    uc->query = cur;
+    if (*cur == '?')
+        cur = find_delim("#", cur, end);
+
+    /* fragment */
+    uc->fragment = cur;
+
+    uc->end = end;
+    return 0;
+}
+
 static void trim_double_dot_url(char *buf, const char *rel, int size)
 {
     const char *p = rel;
diff --git a/libavformat/url.h b/libavformat/url.h
index 4750bfff82..ec70ce14c7 100644
--- a/libavformat/url.h
+++ b/libavformat/url.h
@@ -340,4 +340,45 @@ const AVClass *ff_urlcontext_child_class_next(const AVClass *prev);
 const URLProtocol **ffurl_get_protocols(const char *whitelist,
                                         const char *blacklist);
 
+typedef struct URLComponents {
+    const char *url;        /**< whole URL, for reference */
+    const char *scheme;     /**< possibly including lavf-specific options */
+    const char *authority;  /**< "//" if it is a real URL */
+    const char *userinfo;   /**< including final '@' if present */
+    const char *host;
+    const char *port;       /**< including initial ':' if present */
+    const char *path;
+    const char *query;      /**< including initial '?' if present */
+    const char *fragment;   /**< including initial '#' if present */
+    const char *end;
+} URLComponents;
+
+#define url_component_end_scheme      authority
+#define url_component_end_authority   userinfo
+#define url_component_end_userinfo    host
+#define url_component_end_host        port
+#define url_component_end_port        path
+#define url_component_end_path        query
+#define url_component_end_query       fragment
+#define url_component_end_fragment    end
+#define url_component_end_authority_full path
+
+#define URL_COMPONENT_HAVE(uc, component) \
+    ((uc).url_component_end_##component > (uc).component)
+
+/**
+ * Parse an URL to find the components.
+ *
+ * Each component runs until the start of the next component,
+ * possibly including a mandatory delimiter.
+ *
+ * @param uc   structure to fill with pointers to the components.
+ * @param url  URL to parse.
+ * @param end  end of the URL, or NULL to parse to the end of string.
+ *
+ * @return  >= 0 for success or an AVERROR code, especially if the URL is
+ *          malformed.
+ */
+int ff_url_decompose(URLComponents *uc, const char *url, const char *end);
+
 #endif /* AVFORMAT_URL_H */
diff --git a/tests/ref/fate/url b/tests/ref/fate/url
index 533ba2cb1e..84cf85abdd 100644
--- a/tests/ref/fate/url
+++ b/tests/ref/fate/url
@@ -1,3 +1,48 @@
+Testing ff_url_decompose:
+
+http://user:pass@ffmpeg:8080/dir/file?query#fragment =>
+  scheme: http:
+  authority: //
+  userinfo: user:pass@
+  host: ffmpeg
+  port: :8080
+  path: /dir/file
+  query: ?query
+  fragment: #fragment
+
+http://ffmpeg/dir/file =>
+  scheme: http:
+  authority: //
+  host: ffmpeg
+  path: /dir/file
+
+file:///dev/null =>
+  scheme: file:
+  authority: //
+  path: /dev/null
+
+file:/dev/null =>
+  scheme: file:
+  path: /dev/null
+
+http://[::1]/dev/null =>
+  scheme: http:
+  authority: //
+  host: [::1]
+  path: /dev/null
+
+http://[::1]:8080/dev/null =>
+  scheme: http:
+  authority: //
+  host: [::1]
+  port: :8080
+  path: /dev/null
+
+//ffmpeg/dev/null =>
+  authority: //
+  host: ffmpeg
+  path: /dev/null
+
 Testing ff_make_absolute_url:
                                             (null) baz                  => baz
                                           /foo/bar baz                  => /foo/baz