[FFmpeg-devel] [PATCH] vf_drawtext: make x and y options parametric

Stefano Sabatini stefasab at gmail.com
Tue Sep 20 20:30:46 CEST 2011


Address trac issue #378.
---
 doc/filters.texi          |   68 ++++++++++++++++++++-
 libavfilter/vf_drawtext.c |  143 ++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 191 insertions(+), 20 deletions(-)

diff --git a/doc/filters.texi b/doc/filters.texi
index 1ab6450..f7f7865 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -724,10 +724,13 @@ parameter @var{text}.
 If both text and textfile are specified, an error is thrown.
 
 @item x, y
-The offsets where text will be drawn within the video frame.
-Relative to the top/left border of the output image.
+The expressions which express the offsets where text will be drawn
+within the video frame. They are relative to the top/left border of the
+output image.
 
-The default value of @var{x} and @var{y} is 0.
+The default value of @var{x} and @var{y} is "0".
+
+See below for the list of accepted constants.
 
 @item fontsize
 The font size to be used for drawing text.
@@ -795,6 +798,43 @@ The size in number of spaces to use for rendering the tab.
 Default value is 4.
 @end table
 
+The parameters for @var{x} and @var{y} are expressions containing the
+following constants:
+
+ at table @option
+ at item E, PI, PHI
+the corresponding mathematical approximated values for e
+(euler number), pi (greek PI), PHI (golden ratio)
+
+ at item w, h
+the input width and heigth
+
+ at item tw, text_w
+the width of the rendered text
+
+ at item th, text_h
+the height of the rendered text
+
+ at item lh, line_h
+the height of each text line
+
+ at item sar
+input sample aspect ratio
+
+ at item dar
+input display aspect ratio, it is the same as (@var{w} / @var{h}) * @var{sar}
+
+ at item hsub, vsub
+horizontal and vertical chroma subsample values. For example for the
+pixel format "yuv422p" @var{hsub} is 2 and @var{vsub} is 1.
+
+ at item n
+the number of input frame, starting from 0
+
+ at item t
+timestamp expressed in seconds, NAN if the input timestamp is unknown
+ at end table
+
 Some examples follow.
 
 @itemize
@@ -808,7 +848,7 @@ drawtext="fontfile=/usr/share/fonts/truetype/freefont/FreeSerif.ttf: text='Test
 @end example
 
 @item
-will draw 'Test Text' with font FreeSerif of size 24 at position x=100
+Draw 'Test Text' with font FreeSerif of size 24 at position x=100
 and y=50 (counting from the top-left corner of the screen), text is
 yellow with a red box around it. Both the text and the box have an
 opacity of 20%.
@@ -821,6 +861,26 @@ drawtext="fontfile=/usr/share/fonts/truetype/freefont/FreeSerif.ttf: text='Test
 Note that the double quotes are not necessary if spaces are not used
 within the parameter list.
 
+ at item
+Show the text at the center of the video frame:
+ at example
+drawtext=fontsize=30:fontfile=FreeSerif.ttf:text='hello world':x=(w-text_w)/2:y=(h-text_h-line_h)/2"
+ at end example
+
+ at item
+Show a text line sliding from right to left in the last row of the video
+frame. The file @file{LONG_LINE} is assumed to contain a single line
+with no newlines.
+ at example
+drawtext=fontsize=15:fontfile=FreeSerif.ttf:text=LONG_LINE:y=h-line_h:x=-50*t
+ at end example
+
+ at item
+Show the content of file @file{CREDITS}, and scroll it down.
+ at example
+drawtext=fontsize=30:fontfile=FreeSerif.ttf:textfile=CREDITS:y=-50*t"
+ at end example
+
 @end itemize
 
 For more information about libfreetype, check:
diff --git a/libavfilter/vf_drawtext.c b/libavfilter/vf_drawtext.c
index d7447c2..ffc2bdf 100644
--- a/libavfilter/vf_drawtext.c
+++ b/libavfilter/vf_drawtext.c
@@ -30,6 +30,7 @@
 #include <time.h>
 
 #include "libavutil/colorspace.h"
+#include "libavutil/eval.h"
 #include "libavutil/file.h"
 #include "libavutil/opt.h"
 #include "libavutil/parseutils.h"
@@ -45,6 +46,46 @@
 #include FT_FREETYPE_H
 #include FT_GLYPH_H
 
+static const char *var_names[] = {
+    "E",
+    "PHI",
+    "PI",
+    "w",             ///< width  of the input video
+    "h",             ///< height of the input video
+    "tw", "text_w",  ///< width  of the rendered text
+    "th", "text_h",  ///< height of the rendered text
+    "lh", "line_h",  ///< height of each line
+    "sar",
+    "dar",
+    "hsub",
+    "vsub",
+    "x",
+    "y",
+    "n",            ///< number of frame
+    "t",            ///< timestamp expressed in seconds
+    NULL
+};
+
+enum var_name {
+    VAR_E,
+    VAR_PHI,
+    VAR_PI,
+    VAR_W,
+    VAR_H,
+    VAR_TW, VAR_TEXT_W,
+    VAR_TH, VAR_TEXT_H,
+    VAR_LH, VAR_LINE_H,
+    VAR_SAR,
+    VAR_DAR,
+    VAR_HSUB,
+    VAR_VSUB,
+    VAR_X,
+    VAR_Y,
+    VAR_N,
+    VAR_T,
+    VAR_VARS_NB
+};
+
 typedef struct {
     const AVClass *class;
     uint8_t *fontfile;              ///< font to be used
@@ -57,6 +98,11 @@ typedef struct {
     char *textfile;                 ///< file with text to be drawn
     int x;                          ///< x position to start drawing text
     int y;                          ///< y position to start drawing text
+    char *x_expr;                   ///< expression for x position
+    char *y_expr;                   ///< expression for y position
+    AVExpr *x_pexpr, *y_pexpr;      ///< parsed expressions for x and y
+    int line_h;                     ///< size of each line
+    int max_glyph_w;                ///< max glyph width
     int shadowx, shadowy;
     unsigned int fontsize;          ///< font size to use
     char *fontcolor_string;         ///< font color as string
@@ -82,6 +128,7 @@ typedef struct {
     uint8_t rgba_map[4];            ///< map RGBA offsets to the positions in the packed RGBA format
     uint8_t *box_line[4];           ///< line used for filling the box background
     int64_t basetime;               ///< base pts time in the real world for display
+    double var_values[VAR_VARS_NB];
 } DrawTextContext;
 
 #define OFFSET(x) offsetof(DrawTextContext, x)
@@ -95,8 +142,8 @@ static const AVOption drawtext_options[]= {
 {"shadowcolor", "set shadow color",  OFFSET(shadowcolor_string), FF_OPT_TYPE_STRING, {.str=NULL},  CHAR_MIN, CHAR_MAX },
 {"box",      "set box",              OFFSET(draw_box),           FF_OPT_TYPE_INT,    {.dbl=0},     0,        1        },
 {"fontsize", "set font size",        OFFSET(fontsize),           FF_OPT_TYPE_INT,    {.dbl=16},    1,        72       },
-{"x",        "set x",                OFFSET(x),                  FF_OPT_TYPE_INT,    {.dbl=0},     0,        INT_MAX  },
-{"y",        "set y",                OFFSET(y),                  FF_OPT_TYPE_INT,    {.dbl=0},     0,        INT_MAX  },
+{"x",        "set x",                OFFSET(x_expr),             FF_OPT_TYPE_STRING, {.str="0"},   CHAR_MIN, CHAR_MAX },
+{"y",        "set y",                OFFSET(y_expr),             FF_OPT_TYPE_STRING, {.str="0"},   CHAR_MIN, CHAR_MAX },
 {"shadowx",  "set x",                OFFSET(shadowx),            FF_OPT_TYPE_INT,    {.dbl=0},     INT_MIN,  INT_MAX  },
 {"shadowy",  "set y",                OFFSET(shadowy),            FF_OPT_TYPE_INT,    {.dbl=0},     INT_MIN,  INT_MAX  },
 {"tabsize",  "set tab size",         OFFSET(tabsize),            FF_OPT_TYPE_INT,    {.dbl=4},     0,        INT_MAX  },
@@ -348,12 +395,20 @@ static av_cold void uninit(AVFilterContext *ctx)
     DrawTextContext *dtext = ctx->priv;
     int i;
 
+    av_expr_free(dtext->x_pexpr); dtext->x_pexpr = NULL;
+    av_expr_free(dtext->y_pexpr); dtext->y_pexpr = NULL;
+
     av_freep(&dtext->fontfile);
     av_freep(&dtext->text);
     av_freep(&dtext->expanded_text);
     av_freep(&dtext->fontcolor_string);
     av_freep(&dtext->boxcolor_string);
     av_freep(&dtext->positions);
+    av_freep(&dtext->x_expr);
+    av_freep(&dtext->y_expr);
+    av_expr_free(dtext->x_pexpr);
+    av_expr_free(dtext->y_pexpr);
+
     dtext->nb_positions = 0;
     av_freep(&dtext->shadowcolor_string);
     av_tree_enumerate(dtext->glyphs, NULL, NULL, glyph_enu_free);
@@ -371,6 +426,7 @@ static av_cold void uninit(AVFilterContext *ctx)
 
 static int config_input(AVFilterLink *inlink)
 {
+    AVFilterContext *ctx = inlink->dst;
     DrawTextContext *dtext = inlink->dst->priv;
     const AVPixFmtDescriptor *pix_desc = &av_pix_fmt_descriptors[inlink->format];
     int ret;
@@ -398,6 +454,26 @@ static int config_input(AVFilterLink *inlink)
         dtext->shadowcolor[3] = rgba[3];
     }
 
+    dtext->var_values[VAR_E]     = M_E;
+    dtext->var_values[VAR_PHI]   = M_PHI;
+    dtext->var_values[VAR_PI]    = M_PI;
+    dtext->var_values[VAR_W]     = inlink->w;
+    dtext->var_values[VAR_H]     = inlink->h;
+    dtext->var_values[VAR_SAR]   = inlink->sample_aspect_ratio.num ? av_q2d(inlink->sample_aspect_ratio) : 1;
+    dtext->var_values[VAR_DAR]   = (double)inlink->w / inlink->h * dtext->var_values[VAR_SAR];
+    dtext->var_values[VAR_HSUB]  = 1<<pix_desc->log2_chroma_w;
+    dtext->var_values[VAR_VSUB]  = 1<<pix_desc->log2_chroma_h;
+    dtext->var_values[VAR_X]     = NAN;
+    dtext->var_values[VAR_Y]     = NAN;
+    dtext->var_values[VAR_N]     = 0;
+    dtext->var_values[VAR_T]     = NAN;
+
+    if ((ret = av_expr_parse(&dtext->x_pexpr, dtext->x_expr, var_names,
+                             NULL, NULL, NULL, NULL, 0, ctx)) < 0 ||
+        (ret = av_expr_parse(&dtext->y_pexpr, dtext->y_expr, var_names,
+                             NULL, NULL, NULL, NULL, 0, ctx)) < 0)
+        return AVERROR(EINVAL);
+
     return 0;
 }
 
@@ -441,6 +517,9 @@ static inline int draw_glyph_yuv(AVFilterBufferRef *picref, FT_Bitmap *bitmap,
 
     for (r = 0; r < bitmap->rows && r+y < height; r++) {
         for (c = 0; c < bitmap->width && c+x < width; c++) {
+            if (c+x < 0 || r+y < 0)
+                continue;
+
             /* get intensity value in the glyph bitmap (source) */
             src_val = GET_BITMAP_VAL(r, c);
             if (!src_val)
@@ -471,6 +550,9 @@ static inline int draw_glyph_rgb(AVFilterBufferRef *picref, FT_Bitmap *bitmap,
 
     for (r = 0; r < bitmap->rows && r+y < height; r++) {
         for (c = 0; c < bitmap->width && c+x < width; c++) {
+
+            if (c+x < 0 || r+y < 0)
+                continue;
             /* get intensity value in the glyph bitmap (source) */
             src_val = GET_BITMAP_VAL(r, c);
             if (!src_val)
@@ -521,7 +603,7 @@ static int draw_glyphs(DrawTextContext *dtext, AVFilterBufferRef *picref,
 {
     char *text = dtext->expanded_text;
     uint32_t code = 0;
-    int i;
+    int i, x1, y1;
     uint8_t *p;
     Glyph *glyph = NULL;
 
@@ -540,13 +622,16 @@ static int draw_glyphs(DrawTextContext *dtext, AVFilterBufferRef *picref,
             glyph->bitmap.pixel_mode != FT_PIXEL_MODE_GRAY)
             return AVERROR(EINVAL);
 
+        x1 = dtext->positions[i].x+dtext->x+x;
+        y1 = dtext->positions[i].y+dtext->y+y;
+
         if (dtext->is_packed_rgb) {
             draw_glyph_rgb(picref, &glyph->bitmap,
-                           dtext->positions[i].x+x, dtext->positions[i].y+y, width, height,
+                           x1, y1, width, height,
                            dtext->pixel_step[0], rgbcolor, dtext->rgba_map);
         } else {
             draw_glyph_yuv(picref, &glyph->bitmap,
-                           dtext->positions[i].x+x, dtext->positions[i].y+y, width, height,
+                           x1, y1, width, height,
                            yuvcolor, dtext->hsub, dtext->vsub);
         }
     }
@@ -560,11 +645,13 @@ static int draw_text(AVFilterContext *ctx, AVFilterBufferRef *picref,
     DrawTextContext *dtext = ctx->priv;
     uint32_t code = 0, prev_code = 0;
     int x = 0, y = 0, i = 0, ret;
-    int max_text_line_h, baseline;
+    int baseline;
     int max_text_line_w = 0, len;
+    int box_w, box_h;
     char *text = dtext->text;
     uint8_t *p;
     int y_min = 32000, y_max = -32000;
+    int x_min = 32000, x_max = -32000;
     FT_Vector delta;
     Glyph *glyph = NULL, *prev_glyph = NULL;
     Glyph dummy = { 0 };
@@ -607,8 +694,8 @@ static int draw_text(AVFilterContext *ctx, AVFilterBufferRef *picref,
         dtext->nb_positions = len;
     }
 
-    x = dtext->x;
-    y = dtext->y;
+    x = 0;
+    y = 0;
 
     /* load and cache glyphs */
     for (i = 0, p = text; *p; i++) {
@@ -622,8 +709,11 @@ static int draw_text(AVFilterContext *ctx, AVFilterBufferRef *picref,
 
         y_min = FFMIN(glyph->bbox.yMin, y_min);
         y_max = FFMAX(glyph->bbox.yMax, y_max);
+        x_min = FFMIN(glyph->bbox.xMin, x_min);
+        x_max = FFMIN(glyph->bbox.xMax, x_max);
     }
-    max_text_line_h = y_max - y_min;
+    dtext->line_h      = y_max - y_min;
+    dtext->max_glyph_w = x_max - x_min;
     baseline    = y_max;
 
     /* compute and save position for each glyph */
@@ -637,9 +727,9 @@ static int draw_text(AVFilterContext *ctx, AVFilterBufferRef *picref,
 
         prev_code = code;
         if (is_newline(code)) {
-            max_text_line_w = FFMAX(max_text_line_w, x - dtext->x);
-            y += max_text_line_h;
-            x = dtext->x;
+            max_text_line_w = FFMAX(max_text_line_w, x);
+            y += dtext->line_h;
+            x = 0;
             continue;
         }
 
@@ -662,12 +752,23 @@ static int draw_text(AVFilterContext *ctx, AVFilterBufferRef *picref,
         else              x += glyph->advance;
     }
 
-    max_text_line_w = FFMIN(width - dtext->x - 1, max_text_line_w);
-    y               = FFMIN(y + max_text_line_h, height - 1);
+    dtext->var_values[VAR_TW] = dtext->var_values[VAR_TEXT_W] = FFMAX(x, max_text_line_w);
+    dtext->var_values[VAR_TH] = dtext->var_values[VAR_TEXT_H] = y + dtext->line_h;
+    dtext->var_values[VAR_LH] = dtext->var_values[VAR_LINE_H] = dtext->line_h;
+
+    dtext->x = dtext->var_values[VAR_X] = av_expr_eval(dtext->x_pexpr, dtext->var_values, NULL);
+    dtext->y = dtext->var_values[VAR_Y] = av_expr_eval(dtext->y_pexpr, dtext->var_values, NULL);
+    dtext->x = dtext->var_values[VAR_X] = av_expr_eval(dtext->x_pexpr, dtext->var_values, NULL);
+
+    dtext->x &= ~((1 << dtext->hsub) - 1);
+    dtext->y &= ~((1 << dtext->vsub) - 1);
+
+    box_w = FFMIN(width - dtext->x - 1, max_text_line_w);
+    box_h = FFMIN(y + dtext->line_h, height - 1) - y;
 
     /* draw box */
     if (dtext->draw_box)
-        drawbox(picref, dtext->x, dtext->y, max_text_line_w, y-dtext->y,
+        drawbox(picref, dtext->x, dtext->y, box_w, box_h,
                 dtext->box_line, dtext->pixel_step, dtext->boxcolor,
                 dtext->hsub, dtext->vsub, dtext->is_packed_rgb, dtext->rgba_map);
 
@@ -689,9 +790,19 @@ static void null_draw_slice(AVFilterLink *link, int y, int h, int slice_dir) { }
 static void end_frame(AVFilterLink *inlink)
 {
     AVFilterLink *outlink = inlink->dst->outputs[0];
+    AVFilterContext *ctx = inlink->dst;
+    DrawTextContext *dtext = inlink->dst->priv;
     AVFilterBufferRef *picref = inlink->cur_buf;
 
-    draw_text(inlink->dst, picref, picref->video->w, picref->video->h);
+    dtext->var_values[VAR_T] = picref->pts == AV_NOPTS_VALUE ?
+        NAN : picref->pts * av_q2d(inlink->time_base);
+
+    draw_text(ctx, picref, picref->video->w, picref->video->h);
+
+    av_log(ctx, AV_LOG_DEBUG, "n:%d t:%f x:%d y:%d\n",
+            (int)dtext->var_values[VAR_N], dtext->var_values[VAR_T], dtext->x, dtext->y);
+
+    dtext->var_values[VAR_N] += 1.0;
 
     avfilter_draw_slice(outlink, 0, picref->video->h, 1);
     avfilter_end_frame(outlink);
-- 
1.7.2.5



More information about the ffmpeg-devel mailing list