ffprobe: add -read_intervals option

This is also useful to test seeking on an input file.

This also addresses trac ticket #1437.

3 files changed, 320 insertions, 2 deletions

diff --git a/Changelog b/Changelog
index 3e4653b746..24fe407719 100644
--- a/Changelog
+++ b/Changelog
@@ -25,6 +25,7 @@ version <next>
   more consistent with other muxers.
 - adelay filter
 - pullup filter ported from libmpcodecs
+- ffprobe -read_intervals option
 
 
 version 2.0:
diff --git a/doc/ffprobe.texi b/doc/ffprobe.texi
index 20f5f4acc7..777dbe7506 100644
--- a/doc/ffprobe.texi
+++ b/doc/ffprobe.texi
@@ -230,6 +230,70 @@ corresponding stream section.
 Count the number of packets per stream and report it in the
 corresponding stream section.
 
+@item -read_intervals @var{read_intervals}
+
+Read only the specified intervals. @var{read_intervals} must be a
+sequence of interval specifications separated by ",".
+@command{ffprobe} will seek to the interval starting point, and will
+continue reading from that.
+
+Each interval is specified by two optional parts, separated by "%".
+
+The first part specifies the interval start position. It is
+interpreted as an abolute position, or as a relative offset from the
+current position if it is preceded by the "+" character. If this first
+part is not specified, no seeking will be performed when reading this
+interval.
+
+The second part specifies the interval end position. It is interpreted
+as an absolute position, or as a relative offset from the current
+position if it is preceded by the "+" character. If the offset
+specification starts with "#", it is interpreted as the number of
+packets to read (not including the flushing packets) from the interval
+start. If no second part is specified, the program will read until the
+end of the input.
+
+Note that seeking is not accurate, thus the actual interval start
+point may be different from the specified position. Also, when an
+interval duration is specified, the absolute end time will be computed
+by adding the duration to the interval start point found by seeking
+the file, rather than to the specified start value.
+
+The formal syntax is given by:
+@example
+@var{INTERVAL}  ::= [@var{START}|+@var{START_OFFSET}][%[@var{END}|+@var{END_OFFSET}]]
+@var{INTERVALS} ::= @var{INTERVAL}[,@var{INTERVALS}]
+@end example
+
+A few examples follow.
+@itemize
+@item
+Seek to time 10, read packets until 20 seconds after the found seek
+point, then seek to position @code{01:30} (1 minute and thirty
+seconds) and read packets until position @code{01:45}.
+@example
+10%+20,01:30%01:45
+@end example
+
+@item
+Read only 42 packets after seeking to position @code{01:23}:
+@example
+01:23%+#42
+@end example
+
+@item
+Read only the first 20 seconds from the start:
+@example
+%+20
+@end example
+
+@item
+Read from the start until position @code{02:30}:
+@example
+%02:30
+@end example
+@end itemize
+
 @item -show_private_data, -private
 Show private data, that is data depending on the format of the
 particular shown element.
diff --git a/ffprobe.c b/ffprobe.c
index 54fef04f0d..bbcdc975e5 100644
--- a/ffprobe.c
+++ b/ffprobe.c
@@ -37,7 +37,9 @@
 #include "libavutil/pixdesc.h"
 #include "libavutil/dict.h"
 #include "libavutil/libm.h"
+#include "libavutil/parseutils.h"
 #include "libavutil/timecode.h"
+#include "libavutil/timestamp.h"
 #include "libavdevice/avdevice.h"
 #include "libswscale/swscale.h"
 #include "libswresample/swresample.h"
@@ -73,6 +75,17 @@ static int show_private_data            = 1;
 static char *print_format;
 static char *stream_specifier;
 
+typedef struct {
+    int id;             ///< identifier
+    int64_t start, end; ///< start, end in second/AV_TIME_BASE units
+    int has_start, has_end;
+    int start_is_offset, end_is_offset;
+    int duration_frames;
+} ReadInterval;
+
+static ReadInterval *read_intervals;
+static int read_intervals_nb = 0;
+
 /* section structure definition */
 
 #define SECTION_MAX_NB_CHILDREN 10
@@ -1593,16 +1606,93 @@ static av_always_inline int process_frame(WriterContext *w,
     return got_frame;
 }
 
-static void read_packets(WriterContext *w, AVFormatContext *fmt_ctx)
+static void log_read_interval(const ReadInterval *interval, void *log_ctx, int log_level)
+{
+    av_log(log_ctx, log_level, "id:%d", interval->id);
+
+    if (interval->has_start) {
+        av_log(log_ctx, log_level, " start:%s%s", interval->start_is_offset ? "+" : "",
+               av_ts2timestr(interval->start, &AV_TIME_BASE_Q));
+    } else {
+        av_log(log_ctx, log_level, " start:N/A");
+    }
+
+    if (interval->has_end) {
+        av_log(log_ctx, log_level, " end:%s", interval->end_is_offset ? "+" : "");
+        if (interval->duration_frames)
+            av_log(log_ctx, log_level, "#%"PRId64, interval->end);
+        else
+            av_log(log_ctx, log_level, "%s", av_ts2timestr(interval->end, &AV_TIME_BASE_Q));
+    } else {
+        av_log(log_ctx, log_level, " end:N/A");
+    }
+
+    av_log(log_ctx, log_level, "\n");
+}
+
+static int read_interval_packets(WriterContext *w, AVFormatContext *fmt_ctx,
+                                 const ReadInterval *interval, int64_t *cur_ts)
 {
     AVPacket pkt, pkt1;
     AVFrame frame;
-    int i = 0;
+    int ret = 0, i = 0, frame_count = 0;
+    int64_t start, end = interval->end;
+    int has_start = 0, has_end = interval->has_end && !interval->end_is_offset;
 
     av_init_packet(&pkt);
 
+    av_log(NULL, AV_LOG_VERBOSE, "Processing read interval ");
+    log_read_interval(interval, NULL, AV_LOG_VERBOSE);
+
+    if (interval->has_start) {
+        int64_t target;
+        if (interval->start_is_offset) {
+            if (*cur_ts == AV_NOPTS_VALUE) {
+                av_log(NULL, AV_LOG_ERROR,
+                       "Could not seek to relative position since current "
+                       "timestamp is not defined\n");
+                ret = AVERROR(EINVAL);
+                goto end;
+            }
+            target = *cur_ts + interval->start;
+        } else {
+            target = interval->start;
+        }
+
+        av_log(NULL, AV_LOG_VERBOSE, "Seeking to read interval start point %s\n",
+               av_ts2timestr(target, &AV_TIME_BASE_Q));
+        if ((ret = avformat_seek_file(fmt_ctx, -1, -INT64_MAX, target, INT64_MAX, 0)) < 0) {
+            av_log(NULL, AV_LOG_ERROR, "Could not seek to position %"PRId64": %s\n",
+                   interval->start, av_err2str(ret));
+            goto end;
+        }
+    }
+
     while (!av_read_frame(fmt_ctx, &pkt)) {
         if (selected_streams[pkt.stream_index]) {
+            AVRational tb = fmt_ctx->streams[pkt.stream_index]->time_base;
+
+            if (pkt.pts != AV_NOPTS_VALUE)
+                *cur_ts = av_rescale_q(pkt.pts, tb, AV_TIME_BASE_Q);
+
+            if (!has_start && *cur_ts != AV_NOPTS_VALUE) {
+                start = *cur_ts;
+                has_start = 1;
+            }
+
+            if (has_start && !has_end && interval->end_is_offset) {
+                end = start + interval->end;
+                has_end = 1;
+            }
+
+            if (interval->end_is_offset && interval->duration_frames) {
+                if (frame_count >= interval->end)
+                    break;
+            } else if (has_end && *cur_ts != AV_NOPTS_VALUE && *cur_ts >= end) {
+                break;
+            }
+
+            frame_count++;
             if (do_read_packets) {
                 if (do_show_packets)
                     show_packet(w, fmt_ctx, &pkt, i++);
@@ -1624,6 +1714,30 @@ static void read_packets(WriterContext *w, AVFormatContext *fmt_ctx)
         if (do_read_frames)
             while (process_frame(w, fmt_ctx, &frame, &pkt) > 0);
     }
+
+end:
+    if (ret < 0) {
+        av_log(NULL, AV_LOG_ERROR, "Could not read packets in interval ");
+        log_read_interval(interval, NULL, AV_LOG_ERROR);
+    }
+    return ret;
+}
+
+static void read_packets(WriterContext *w, AVFormatContext *fmt_ctx)
+{
+    int i, ret = 0;
+    int64_t cur_ts = fmt_ctx->start_time;
+
+    if (read_intervals_nb == 0) {
+        ReadInterval interval = (ReadInterval) { .has_start = 0, .has_end = 0 };
+        ret = read_interval_packets(w, fmt_ctx, &interval, &cur_ts);
+    } else {
+        for (i = 0; i < read_intervals_nb; i++) {
+            ret = read_interval_packets(w, fmt_ctx, &read_intervals[i], &cur_ts);
+            if (ret < 0)
+                break;
+        }
+    }
 }
 
 static void show_stream(WriterContext *w, AVFormatContext *fmt_ctx, int stream_idx, int in_program)
@@ -2229,6 +2343,143 @@ void show_help_default(const char *opt, const char *arg)
     show_help_children(avformat_get_class(), AV_OPT_FLAG_DECODING_PARAM);
 }
 
+/**
+ * Parse interval specification, according to the format:
+ * INTERVAL ::= [START|+START_OFFSET][%[END|+END_OFFSET]]
+ * INTERVALS ::= INTERVAL[,INTERVALS]
+*/
+static int parse_read_interval(const char *interval_spec,
+                               ReadInterval *interval)
+{
+    int ret = 0;
+    char *next, *p, *spec = av_strdup(interval_spec);
+    if (!spec)
+        return AVERROR(ENOMEM);
+
+    if (!*spec) {
+        av_log(NULL, AV_LOG_ERROR, "Invalid empty interval specification\n");
+        ret = AVERROR(EINVAL);
+        goto end;
+    }
+
+    p = spec;
+    next = strchr(spec, '%');
+    if (next)
+        *next++ = 0;
+
+    /* parse first part */
+    if (*p) {
+        interval->has_start = 1;
+
+        if (*p == '+') {
+            interval->start_is_offset = 1;
+            p++;
+        } else {
+            interval->start_is_offset = 0;
+        }
+
+        ret = av_parse_time(&interval->start, p, 1);
+        if (ret < 0) {
+            av_log(NULL, AV_LOG_ERROR, "Invalid interval start specification '%s'\n", p);
+            goto end;
+        }
+    } else {
+        interval->has_start = 0;
+    }
+
+    /* parse second part */
+    p = next;
+    if (p && *p) {
+        int64_t us;
+        interval->has_end = 1;
+
+        if (*p == '+') {
+            interval->end_is_offset = 1;
+            p++;
+        } else {
+            interval->end_is_offset = 0;
+        }
+
+        if (interval->end_is_offset && *p == '#') {
+            long long int lli;
+            char *tail;
+            interval->duration_frames = 1;
+            p++;
+            lli = strtoll(p, &tail, 10);
+            if (*tail || lli < 0) {
+                av_log(NULL, AV_LOG_ERROR,
+                       "Invalid or negative value '%s' for duration number of frames\n", p);
+                goto end;
+            }
+            interval->end = lli;
+        } else {
+            ret = av_parse_time(&us, p, 1);
+            if (ret < 0) {
+                av_log(NULL, AV_LOG_ERROR, "Invalid interval end/duration specification '%s'\n", p);
+                goto end;
+            }
+            interval->end = us;
+        }
+    } else {
+        interval->has_end = 0;
+    }
+
+end:
+    av_free(spec);
+    return ret;
+}
+
+static int parse_read_intervals(const char *intervals_spec)
+{
+    int ret, n, i;
+    char *p, *spec = av_strdup(intervals_spec);
+    if (!spec)
+        return AVERROR(ENOMEM);
+
+    /* preparse specification, get number of intervals */
+    for (n = 0, p = spec; *p; p++)
+        if (*p == ',')
+            n++;
+    n++;
+
+    read_intervals = av_malloc(n * sizeof(*read_intervals));
+    if (!read_intervals) {
+        ret = AVERROR(ENOMEM);
+        goto end;
+    }
+    read_intervals_nb = n;
+
+    /* parse intervals */
+    p = spec;
+    for (i = 0; i < n; i++) {
+        char *next = strchr(p, ',');
+        if (next)
+            *next++ = 0;
+
+        read_intervals[i].id = i;
+        ret = parse_read_interval(p, &read_intervals[i]);
+        if (ret < 0) {
+            av_log(NULL, AV_LOG_ERROR, "Error parsing read interval #%d '%s'\n",
+                   i, p);
+            goto end;
+        }
+        av_log(NULL, AV_LOG_VERBOSE, "Parsed log interval ");
+        log_read_interval(&read_intervals[i], NULL, AV_LOG_VERBOSE);
+        p = next;
+        av_assert0(i <= read_intervals_nb);
+    }
+    av_assert0(i == read_intervals_nb);
+
+end:
+    av_free(spec);
+    return ret;
+}
+
+static int opt_read_intervals(void *optctx, const char *opt, const char *arg)
+{
+    return parse_read_intervals(arg);
+}
+
 static int opt_pretty(void *optctx, const char *opt, const char *arg)
 {
     show_value_unit              = 1;
@@ -2327,6 +2578,7 @@ static const OptionDef real_options[] = {
     { "show_private_data", OPT_BOOL, {(void*)&show_private_data}, "show private data" },
     { "private",           OPT_BOOL, {(void*)&show_private_data}, "same as show_private_data" },
     { "bitexact", OPT_BOOL, {&do_bitexact}, "force bitexact output" },
+    { "read_intervals", HAS_ARG, {.func_arg = opt_read_intervals}, "set read intervals", "read_intervals" },
     { "default", HAS_ARG | OPT_AUDIO | OPT_VIDEO | OPT_EXPERT, {.func_arg = opt_default}, "generic catch all option", "" },
     { "i", HAS_ARG, {.func_arg = opt_input_file_i}, "read specified file", "input_file"},
     { NULL, },
@@ -2439,6 +2691,7 @@ int main(int argc, char **argv)
 
 end:
     av_freep(&print_format);
+    av_freep(&read_intervals);
 
     uninit_opts();
     for (i = 0; i < FF_ARRAY_ELEMS(sections); i++)