GStreamer基础教程09——收集媒体信息

目标

      有时你需要快速的了解一个文件（或URI）包含的媒体格式或者看看是否支持这种格式。当然你可以创建一个pipeline，设置运行，观察总线上的消息，但GStreamer提供了一个工具可以帮你做这些。本教程主要讲述：

      如何获得一个URI上的信息

      如何确定一个URI是可以播放的

介绍

      GstDiscover是一个在pbutils库提供的工具，接受输入URI或者URI列表，返回它们的信息。这个工具可以工作在同步或者异步模式下。

      在同步模式下，只有一个API可以用，就是gst_discoverer_discover_uri()，这个API会阻塞线程直到得到需要的信息。因为阻塞会带来GUI上很糟糕的体验，所以基于UI的应用主要使用异步模式，本教程也是基于异步模式的。

      检测到的信息会包括codec的描述，流的拓扑结构和可以获得的元数据。

<span style="font-size:14px;">As an example, this is the result of discovering (Click to expand)
Duration: 0:00:52.250000000
Tags:
  video codec: On2 VP8
  language code: en
  container format: Matroska
  application name: ffmpeg2theora-0.24
  encoder: Xiph.Org libVorbis I 20090709
  encoder version: 0
  audio codec: Vorbis
  nominal bitrate: 80000
  bitrate: 80000
Seekable: yes
Stream information:
  container: WebM
    audio: Vorbis
      Tags:
        language code: en
        container format: Matroska
        audio codec: Vorbis
        application name: ffmpeg2theora-0.24
        encoder: Xiph.Org libVorbis I 20090709
        encoder version: 0
        nominal bitrate: 80000
        bitrate: 80000
    video: VP8
      Tags:
        video codec: VP8 video
        container format: Matroskaspan>

      下面的代码试着通过命令行的方式来运行discover工具来解析URI的内容，输出获得的信息。

      这是gst-discoverer工具使用的简单版本，这个应用仅仅显示数据，甚至不提供播放功能。

GStreamer Discoverer

<span style="font-size:14px;">#include <string.h>
#include <gst/gst.h>
#include <gst/pbutils/pbutils.h>

/* Structure to contain all our information, so we can pass it around */
typedef struct _CustomData {
  GstDiscoverer *discoverer;
  GMainLoop *loop;
} CustomData;

/* Print a tag in a human-readable format (name: value) */
static void print_tag_foreach (const GstTagList *tags, const gchar *tag, gpointer user_data) {
  GValue val = { 0, };
  gchar *str;
  gint depth = GPOINTER_TO_INT (user_data);

  gst_tag_list_copy_value (&val, tags, tag);

  if (G_VALUE_HOLDS_STRING (&val))
    str = g_value_dup_string (&val);
  else
    str = gst_value_serialize (&val);

  g_print ("%*s%s: %s\n", 2 * depth, " ", gst_tag_get_nick (tag), str);
  g_free (str);

  g_value_unset (&val);
}

/* Print information regarding a stream */
static void print_stream_info (GstDiscovererStreamInfo *info, gint depth) {
  gchar *desc = NULL;
  GstCaps *caps;
  const GstTagList *tags;

  caps = gst_discoverer_stream_info_get_caps (info);

  if (caps) {
    if (gst_caps_is_fixed (caps))
      desc = gst_pb_utils_get_codec_description (caps);
    else
      desc = gst_caps_to_string (caps);
    gst_caps_unref (caps);
  }

  g_print ("%*s%s: %s\n", 2 * depth, " ", gst_discoverer_stream_info_get_stream_type_nick (info), (desc ? desc : ""));

  if (desc) {
    g_free (desc);
    desc = NULL;
  }

  tags = gst_discoverer_stream_info_get_tags (info);
  if (tags) {
    g_print ("%*sTags:\n", 2 * (depth + 1), " ");
    gst_tag_list_foreach (tags, print_tag_foreach, GINT_TO_POINTER (depth + 2));
  }
}

/* Print information regarding a stream and its substreams, if any */
static void print_topology (GstDiscovererStreamInfo *info, gint depth) {
  GstDiscovererStreamInfo *next;

  if (!info)
    return;

  print_stream_info (info, depth);

  next = gst_discoverer_stream_info_get_next (info);
  if (next) {
    print_topology (next, depth + 1);
    gst_discoverer_stream_info_unref (next);
  } else if (GST_IS_DISCOVERER_CONTAINER_INFO (info)) {
    GList *tmp, *streams;

    streams = gst_discoverer_container_info_get_streams (GST_DISCOVERER_CONTAINER_INFO (info));
    for (tmp = streams; tmp; tmp = tmp->next) {
      GstDiscovererStreamInfo *tmpinf = (GstDiscovererStreamInfo *) tmp->data;
      print_topology (tmpinf, depth + 1);
    }
    gst_discoverer_stream_info_list_free (streams);
  }
}

/* This function is called every time the discoverer has information regarding
 * one of the URIs we provided.*/
static void on_discovered_cb (GstDiscoverer *discoverer, GstDiscovererInfo *info, GError *err, CustomData *data) {
  GstDiscovererResult result;
  const gchar *uri;
  const GstTagList *tags;
  GstDiscovererStreamInfo *sinfo;

  uri = gst_discoverer_info_get_uri (info);
  result = gst_discoverer_info_get_result (info);
  switch (result) {
    case GST_DISCOVERER_URI_INVALID:
      g_print ("Invalid URI '%s'\n", uri);
      break;
    case GST_DISCOVERER_ERROR:
      g_print ("Discoverer error: %s\n", err->message);
      break;
    case GST_DISCOVERER_TIMEOUT:
      g_print ("Timeout\n");
      break;
    case GST_DISCOVERER_BUSY:
      g_print ("Busy\n");
      break;
    case GST_DISCOVERER_MISSING_PLUGINS:{
      const GstStructure *s;
      gchar *str;

      s = gst_discoverer_info_get_misc (info);
      str = gst_structure_to_string (s);

      g_print ("Missing plugins: %s\n", str);
      g_free (str);
      break;
    }
    case GST_DISCOVERER_OK:
      g_print ("Discovered '%s'\n", uri);
      break;
  }

  if (result != GST_DISCOVERER_OK) {
    g_printerr ("This URI cannot be played\n");
    return;
  }

  /* If we got no error, show the retrieved information */

  g_print ("\nDuration: %" GST_TIME_FORMAT "\n", GST_TIME_ARGS (gst_discoverer_info_get_duration (info)));

  tags = gst_discoverer_info_get_tags (info);
  if (tags) {
    g_print ("Tags:\n");
    gst_tag_list_foreach (tags, print_tag_foreach, GINT_TO_POINTER (1));
  }

  g_print ("Seekable: %s\n", (gst_discoverer_info_get_seekable (info) ? "yes" : "no"));

  g_print ("\n");

  sinfo = gst_discoverer_info_get_stream_info (info);
  if (!sinfo)
    return;

  g_print ("Stream information:\n");

  print_topology (sinfo, 1);

  gst_discoverer_stream_info_unref (sinfo);

  g_print ("\n");
}

/* This function is called when the discoverer has finished examining
 * all the URIs we provided.*/
static void on_finished_cb (GstDiscoverer *discoverer, CustomData *data) {
  g_print ("Finished discovering\n");

  g_main_loop_quit (data->loop);
}

int main (int argc, char **argv) {
  CustomData data;
  GError *err = NULL;
  gchar *uri = "";

  /* if a URI was provided, use it instead of the default one */
  if (argc > 1) {
    uri = argv[1];
  }

  /* Initialize cumstom data structure */
  memset (&data, 0, sizeof (data));

  /* Initialize GStreamer */
  gst_init (&argc, &argv);

  g_print ("Discovering '%s'\n", uri);

  /* Instantiate the Discoverer */
  data.discoverer = gst_discoverer_new (5 * GST_SECOND, &err);
  if (!data.discoverer) {
    g_print ("Error creating discoverer instance: %s\n", err->message);
    g_clear_error (&err);
    return -1;
  }

  /* Connect to the interesting signals */
  g_signal_connect (data.discoverer, "discovered", G_CALLBACK (on_discovered_cb), &data);
  g_signal_connect (data.discoverer, "finished", G_CALLBACK (on_finished_cb), &data);

  /* Start the discoverer process (nothing to do yet) */
  gst_discoverer_start (data.discoverer);

  /* Add a request to process asynchronously the URI passed through the command line */
  if (!gst_discoverer_discover_uri_async (data.discoverer, uri)) {
    g_print ("Failed to start discovering URI '%s'\n", uri);
    g_object_unref (data.discoverer);
    return -1;
  }

  /* Create a GLib Main Loop and set it to run, so we can wait for the signals */
  data.loop = g_main_loop_new (NULL, FALSE);
  g_main_loop_run (data.loop);

  /* Stop the discoverer process */
  gst_discoverer_stop (data.discoverer);

  /* Free resources */
  g_object_unref (data.discoverer);
  g_main_loop_unref (data.loop);

  return 0;
}span>

工作流程

      下面是使用GstDiscoverer的主要步骤。

"font-size:14px;">  /* Instantiate the Discoverer */
  data.discoverer = gst_discoverer_new (55 * GST_SECOND, &err);
  if (!data.discoverer) {
    g_print ("Error creating discoverer instance: %s\n", err->message);
    g_clear_error (&err);
    return -1;
  }

      gst_discover_new()会创建一个Discoverer对象，第一个参数是超时时间（使用纳秒做单位）。

"font-size:14px;">  /* Connect to the interesting signals */
  g_signal_connect (data.discoverer, "discovered", G_CALLBACK (on_discovered_cb), &data);
  g_signal_connect (data.discoverer, "finished", G_CALLBACK (on_finished_cb), &data);

      像平常一样对必要的的信号注册回调，我们在他们的回调里面继续讨论。

"font-size:14px;">  /* Start the discoverer process (nothing to do yet) */
  gst_discoverer_start (data.discoverer);

      gst_discover_start()启动检查进程，但我们还没有提供URI，下面就是提供URI了：

"font-size:14px;">  /* Add a request to process asynchronously the URI passed through the command line */
  if (!gst_discoverer_discover_uri_async (data.discoverer, uri)) {
    g_print ("Failed to start discovering URI '%s'\n", uri);
    g_object_unref (data.discoverer);
    return -1;
  }

      gst_discoverer_discover_uri_async()会把需要检查的URI放入队列，这个函数支持把多个URI入队。在检查过程把所有的URI都检查过之后，会调用注册的回调函数。

"font-size:14px;">  /* Create a GLib Main Loop and set it to run, so we can wait for the signals */
  data.loop = g_main_loop_new (NULL, FALSE);
  g_main_loop_run (data.loop);

      GLib已经在运行主循环了，我们在on_finished_cb回调中调用g_main_loop_quit()来退出主循环。

"font-size:14px;">  /* Stop the discoverer process */
  gst_discoverer_stop (data.discoverer);

      一旦我们检查结束，我们会调用gst_discoverer_stop()来停止，并且调用g_object_unref()来释放资源。

      现在让我们来看一下我们注册的回调函数：

"font-size:14px;">/* This function is called every time the discoverer has information regarding
 * one of the URIs we provided.*/
static void on_discovered_cb (GstDiscoverer *discoverer, GstDiscovererInfo *info, GError *err, CustomData *data) {
  GstDiscovererResult result;
  const gchar *uri;
  const GstTagList *tags;
  GstDiscovererStreamInfo *sinfo;

  uri = gst_discoverer_info_get_uri (info);
  result = gst_discoverer_info_get_result (info);

      当我们运行到这些代码时，discoverer已经完成了一个URI的检查了，用GstDiscovererInfo这个数据结构把内容传给我们。

      这里第一步是用gst_discoverer_info_get_uri()方法去获得调用这个回调的URI（因为可能存在多个URI），然后通过gst_discoverer_info_get_result()方法来获得数据。

switch (result) {
  case GST_DISCOVERER_URI_INVALID:
    g_print ("Invalid URI '%s'\n", uri);
    break;
  case GST_DISCOVERER_ERROR:
    g_print ("Discoverer error: %s\n", err->message);
    break;
  case GST_DISCOVERER_TIMEOUT:
    g_print ("Timeout\n");
    break;
  case GST_DISCOVERER_BUSY:
    g_print ("Busy\n");
    break;
  case GST_DISCOVERER_MISSING_PLUGINS:{
    const GstStructure *s;
    gchar *str;

    s = gst_discoverer_info_get_misc (info);
    str = gst_structure_to_string (s);

    g_print ("Missing plugins: %s\n", str);
    g_free (str);
    break;
  }
  case GST_DISCOVERER_OK:
    g_print ("Discovered '%s'\n", uri);
    break;
}

if (result != GST_DISCOVERER_OK) {
  g_printerr ("This URI cannot be played\n");
  return;
}

      正如代码显示的那样，除了GST_DISCOVERER_OK之外，任何一个结果都意味着有某种问题，这个URI不能播放。不能播放的原因是多种多样的，但枚举出来后也比较清晰（GST_DISCOVERER_BUSY只可能在同步模式下出现，这里是不可能出现的）。

      如果没有发生错误，那么可以用gst_discoverer_info_get_*系列方法从GstDiscovererInfo这个结构里面获得数据了。比如，用gst_discoverer_info_get_duration()方法可以获得播放总长度。

      信息的位是由列表组成的，就像标签和流信息，需要再解析一下：

tags = gst_discoverer_info_get_tags (info);
if (tags) {
  g_print ("Tags:\n");
  gst_tag_list_foreach (tags, print_tag_foreach, GINT_TO_POINTER (1));
}

      标签是附着在媒体上得元数据。它们可以用gst_tag_list_foreach()方法来检查，每检查到一个标签就调用一次print_tag_foreach()。至于print_tag_foreach()方法的代码比较浅显，可以直接读懂。

sinfo = gst_discoverer_info_get_stream_info (info);
if (!sinfo)
  return;

g_print ("Stream information:\n");

print_topology (sinfo, 1);

gst_discoverer_stream_info_unref (sinfo);

      gst_discoverer_info_get_stream_info()会返回一个GstDiscovererStreamInfo类型的数据，print_topology()函数会解析这个数据结构，然后调用gst_discoverer_stream_info_unref()来释放资源。

/* Print information regarding a stream and its substreams, if any */
static void print_topology (GstDiscovererStreamInfo *info, gint depth) {
  GstDiscovererStreamInfo *next;

  if (!info)
    return;

  print_stream_info (info, depth);

  next = gst_discoverer_stream_info_get_next (info);
  if (next) {
    print_topology (next, depth + 1);
    gst_discoverer_stream_info_unref (next);
  } else if (GST_IS_DISCOVERER_CONTAINER_INFO (info)) {
    GList *tmp, *streams;

    streams = gst_discoverer_container_info_get_streams (GST_DISCOVERER_CONTAINER_INFO (info));
    for (tmp = streams; tmp; tmp = tmp->next) {
      GstDiscovererStreamInfo *tmpinf = (GstDiscovererStreamInfo *) tmp->data;
      print_topology (tmpinf, depth + 1);
    }
    gst_discoverer_stream_info_list_free (streams);
  }
}

      print_stream_info()函数的代码也是很简单直接的，它也调用了print_tag_foreach方法来打印流的capabilities和相关联的tags。

      print_topology方法会寻找下一个流来显示。如果get_discoverer_stream_info_get_next()返回一个非空流信息的话，它需要被显示。另一方面，如果我们是一个容器，我们每一个用get_discoverer_container_info_get_streams()方法获得的子流都需要递归的调用print_topology方法。当然，如果我们是一个叶子流了，就不在需要继续递归下去了。