blackteay/ffmpeg-python
1
0
Fork 0
mirror of https://github.com/kkroening/ffmpeg-python.git synced 2025-04-05 20:11:11 +08:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into feature/17

Browse Source 
Conflicts:
	ffmpeg/_filters.py
	ffmpeg/_utils.py
	ffmpeg/nodes.py
	ffmpeg/tests/test_ffmpeg.py
This commit is contained in:
Karl Kroening 2017-07-12 02:08:19 -06:00
commit 7b2d8b63fc
4 changed files with 248 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

148
ffmpeg/_filters.py
View File

@ -1,9 +1,7 @@
from __future__ import unicode_literals
from .nodes import (
FilterNode,
filter_operator,
)
from .nodes import FilterNode, filter_operator
from ._utils import escape_chars
@filter_operator()
@ -179,6 +177,148 @@ def drawbox(stream, x, y, width, height, color, thickness=None, **kwargs):
return FilterNode(stream, drawbox.__name__, args=[x, y, width, height, color], kwargs=kwargs).stream()
@filter_operator()
def drawtext(stream, text=None, x=0, y=0, escape_text=True, **kwargs):
"""Draw a text string or text from a specified file on top of a video, using the libfreetype library.
To enable compilation of this filter, you need to configure FFmpeg with ``--enable-libfreetype``. To enable default
font fallback and the font option you need to configure FFmpeg with ``--enable-libfontconfig``. To enable the
text_shaping option, you need to configure FFmpeg with ``--enable-libfribidi``.
Args:
box: Used to draw a box around text using the background color. The value must be either 1 (enable) or 0
(disable). The default value of box is 0.
boxborderw: Set the width of the border to be drawn around the box using boxcolor. The default value of
boxborderw is 0.
boxcolor: The color to be used for drawing box around text. For the syntax of this option, check the "Color"
section in the ffmpeg-utils manual. The default value of boxcolor is "white".
line_spacing: Set the line spacing in pixels of the border to be drawn around the box using box. The default
value of line_spacing is 0.
borderw: Set the width of the border to be drawn around the text using bordercolor. The default value of
borderw is 0.
bordercolor: Set the color to be used for drawing border around text. For the syntax of this option, check the
"Color" section in the ffmpeg-utils manual. The default value of bordercolor is "black".
expansion: Select how the text is expanded. Can be either none, strftime (deprecated) or normal (default). See
the Text expansion section below for details.
basetime: Set a start time for the count. Value is in microseconds. Only applied in the deprecated strftime
expansion mode. To emulate in normal expansion mode use the pts function, supplying the start time (in
seconds) as the second argument.
fix_bounds: If true, check and fix text coords to avoid clipping.
fontcolor: The color to be used for drawing fonts. For the syntax of this option, check the "Color" section in
the ffmpeg-utils manual. The default value of fontcolor is "black".
fontcolor_expr: String which is expanded the same way as text to obtain dynamic fontcolor value. By default
this option has empty value and is not processed. When this option is set, it overrides fontcolor option.
font: The font family to be used for drawing text. By default Sans.
fontfile: The font file to be used for drawing text. The path must be included. This parameter is mandatory if
the fontconfig support is disabled.
alpha: Draw the text applying alpha blending. The value can be a number between 0.0 and 1.0. The expression
accepts the same variables x, y as well. The default value is 1. Please see fontcolor_expr.
fontsize: The font size to be used for drawing text. The default value of fontsize is 16.
text_shaping: If set to 1, attempt to shape the text (for example, reverse the order of right-to-left text and
join Arabic characters) before drawing it. Otherwise, just draw the text exactly as given. By default 1 (if
supported).
ft_load_flags: The flags to be used for loading the fonts. The flags map the corresponding flags supported by
libfreetype, and are a combination of the following values:
* ``default``
* ``no_scale``
* ``no_hinting``
* ``render``
* ``no_bitmap``
* ``vertical_layout``
* ``force_autohint``
* ``crop_bitmap``
* ``pedantic``
* ``ignore_global_advance_width``
* ``no_recurse``
* ``ignore_transform``
* ``monochrome``
* ``linear_design``
* ``no_autohint``
Default value is "default". For more information consult the documentation for the FT_LOAD_* libfreetype
flags.
shadowcolor: The color to be used for drawing a shadow behind the drawn text. For the syntax of this option,
check the "Color" section in the ffmpeg-utils manual. The default value of shadowcolor is "black".
shadowx: The x offset for the text shadow position with respect to the position of the text. It can be either
positive or negative values. The default value is "0".
shadowy: The y offset for the text shadow position with respect to the position of the text. It can be either
positive or negative values. The default value is "0".
start_number: The starting frame number for the n/frame_num variable. The default value is "0".
tabsize: The size in number of spaces to use for rendering the tab. Default value is 4.
timecode: Set the initial timecode representation in "hh:mm:ss[:;.]ff" format. It can be used with or without
text parameter. timecode_rate option must be specified.
rate: Set the timecode frame rate (timecode only).
timecode_rate: Alias for ``rate``.
r: Alias for ``rate``.
tc24hmax: If set to 1, the output of the timecode option will wrap around at 24 hours. Default is 0 (disabled).
text: The text string to be drawn. The text must be a sequence of UTF-8 encoded characters. This parameter is
mandatory if no file is specified with the parameter textfile.
textfile: A text file containing text to be drawn. The text must be a sequence of UTF-8 encoded characters.
This parameter is mandatory if no text string is specified with the parameter text. If both text and
textfile are specified, an error is thrown.
reload: If set to 1, the textfile will be reloaded before each frame. Be sure to update it atomically, or it
may be read partially, or even fail.
x: The expression which specifies the offset where text will be drawn within the video frame. It is relative to
the left border of the output image. The default value is "0".
y: The expression which specifies the offset where text will be drawn within the video frame. It is relative to
the top border of the output image. The default value is "0". See below for the list of accepted constants
and functions.
Expression constants:
The parameters for x and y are expressions containing the following constants and functions:
dar: input display aspect ratio, it is the same as ``(w / h) * sar``
hsub: horizontal chroma subsample values. For example for the pixel format "yuv422p" hsub is 2 and vsub
is 1.
vsub: vertical chroma subsample values. For example for the pixel format "yuv422p" hsub is 2 and vsub
is 1.
line_h: the height of each text line
lh: Alias for ``line_h``.
main_h: the input height
h: Alias for ``main_h``.
H: Alias for ``main_h``.
main_w: the input width
w: Alias for ``main_w``.
W: Alias for ``main_w``.
ascent: the maximum distance from the baseline to the highest/upper grid coordinate used to place a
glyph outline point, for all the rendered glyphs. It is a positive value, due to the grid's
orientation with the Y axis upwards.
max_glyph_a: Alias for ``ascent``.
descent: the maximum distance from the baseline to the lowest grid coordinate used to place a glyph
outline point, for all the rendered glyphs. This is a negative value, due to the grid's
orientation, with the Y axis upwards.
max_glyph_d: Alias for ``descent``.
max_glyph_h: maximum glyph height, that is the maximum height for all the glyphs contained in the
rendered text, it is equivalent to ascent - descent.
max_glyph_w: maximum glyph width, that is the maximum width for all the glyphs contained in the
rendered text
n: the number of input frame, starting from 0
rand(min, max): return a random number included between min and max
sar: The input sample aspect ratio.
t: timestamp expressed in seconds, NAN if the input timestamp is unknown
text_h: the height of the rendered text
th: Alias for ``text_h``.
text_w: the width of the rendered text
tw: Alias for ``text_w``.
x: the x offset coordinates where the text is drawn.
y: the y offset coordinates where the text is drawn.
These parameters allow the x and y expressions to refer each other, so you can for example specify
``y=x/dar``.
Official documentation: `drawtext <https://ffmpeg.org/ffmpeg-filters.html#drawtext>`__
"""
if text is not None:
if escape_text:
text = escape_chars(text, '\\\'%')
kwargs['text'] = text
if x != 0:
kwargs['x'] = x
if y != 0:
kwargs['y'] = y
return filter_(stream, drawtext.__name__, **kwargs)
@filter_operator()
def concat(*streams, **kwargs):
"""Concatenate audio and video streams, joining them together one after the other.

14
ffmpeg/_utils.py
View File

@ -1,4 +1,4 @@
from __future__ import unicode_literals
from __future__ import unicode_literals
from builtins import str
from past.builtins import basestring
@ -29,3 +29,15 @@ def get_hash(item):
def get_hash_int(item):
return int(get_hash(item), base=16)
def escape_chars(text, chars):
"""Helper function to escape uncomfortable characters."""
text = str(text)
chars = list(set(chars))
if '\\' in chars:
chars.remove('\\')
chars.insert(0, '\\')
for ch in chars:
text = text.replace(ch, '\\' + ch)
return text

19
ffmpeg/nodes.py
View File

@ -1,7 +1,7 @@
from __future__ import unicode_literals
from .dag import KwargReprNode
from ._utils import get_hash_int
from ._utils import escape_chars, get_hash_int
from builtins import object
import os
@ -148,20 +148,29 @@ class FilterNode(Node):
kwargs=kwargs
)
"""FilterNode"""
def _get_filter(self, outgoing_edges):
args = self.args
kwargs = self.kwargs
if self.name == 'split':
args = [len(outgoing_edges)]
arg_params = ['{}'.format(arg) for arg in args]
kwarg_params = ['{}={}'.format(k, kwargs[k]) for k in sorted(kwargs)]
out_args = [escape_chars(x, '\\\'=:') for x in args]
out_kwargs = {}
for k, v in kwargs.items():
k = escape_chars(k, '\\\'=:')
v = escape_chars(v, '\\\'=:')
out_kwargs[k] = v
arg_params = [escape_chars(v, '\\\'=:') for v in out_args]
kwarg_params = ['{}={}'.format(k, out_kwargs[k]) for k in sorted(out_kwargs)]
params = arg_params + kwarg_params
params_text = self.name
params_text = escape_chars(self.name, '\\\'=:')
if params:
params_text += '={}'.format(':'.join(params))
return params_text
return escape_chars(params_text, '\\\'[],;')
class OutputNode(Node):

78
ffmpeg/tests/test_ffmpeg.py
View File

@ -1,9 +1,11 @@
from __future__ import unicode_literals
import ffmpeg
import os
import pytest
import subprocess
import random
import re
import subprocess
TEST_DIR = os.path.dirname(__file__)
@ -17,6 +19,13 @@ TEST_OUTPUT_FILE2 = os.path.join(SAMPLE_DATA_DIR, 'out2.mp4')
subprocess.check_call(['ffmpeg', '-version'])
def test_escape_chars():
assert ffmpeg._utils.escape_chars('a:b', ':') == 'a\:b'
assert ffmpeg._utils.escape_chars('a\\:b', ':\\') == 'a\\\\\\:b'
assert ffmpeg._utils.escape_chars('a:b,c[d]e%{}f\'g\'h\\i', '\\\':,[]%') == 'a\\:b\\,c\\[d\\]e\\%{}f\\\'g\\\'h\\\\i'
assert ffmpeg._utils.escape_chars(123, ':\\') == '123'
def test_fluent_equality():
base1 = ffmpeg.input('dummy1.mp4')
base2 = ffmpeg.input('dummy1.mp4')
@ -134,6 +143,73 @@ def test_get_args_complex_filter():
]
def test_filter_normal_arg_escape():
"""Test string escaping of normal filter args (e.g. ``font`` param of ``drawtext`` filter)."""
def _get_drawtext_font_repr(font):
"""Build a command-line arg using drawtext ``font`` param and extract the ``-filter_complex`` arg."""
args = (ffmpeg
.input('in')
.drawtext('test', font='a{}b'.format(font))
.output('out')
.get_args()
)
assert args[:3] == ['-i', 'in', '-filter_complex']
assert args[4:] == ['-map', '[s0]', 'out']
match = re.match(r'\[0\]drawtext=font=a((.|\n)*)b:text=test\[s0\]', args[3], re.MULTILINE)
assert match is not None, 'Invalid -filter_complex arg: {!r}'.format(args[3])
return match.group(1)
expected_backslash_counts = {
'x': 0,
'\'': 3,
'\\': 3,
'%': 0,
':': 2,
',': 1,
'[': 1,
']': 1,
'=': 2,
'\n': 0,
}
for ch, expected_backslash_count in expected_backslash_counts.items():
expected = '{}{}'.format('\\' * expected_backslash_count, ch)
actual = _get_drawtext_font_repr(ch)
assert expected == actual
def test_filter_text_arg_str_escape():
"""Test string escaping of normal filter args (e.g. ``text`` param of ``drawtext`` filter)."""
def _get_drawtext_text_repr(text):
"""Build a command-line arg using drawtext ``text`` param and extract the ``-filter_complex`` arg."""
args = (ffmpeg
.input('in')
.drawtext('a{}b'.format(text))
.output('out')
.get_args()
)
assert args[:3] == ['-i', 'in', '-filter_complex']
assert args[4:] == ['-map', '[s0]', 'out']
match = re.match(r'\[0\]drawtext=text=a((.|\n)*)b\[s0\]', args[3], re.MULTILINE)
assert match is not None, 'Invalid -filter_complex arg: {!r}'.format(args[3])
return match.group(1)
expected_backslash_counts = {
'x': 0,
'\'': 7,
'\\': 7,
'%': 4,
':': 2,
',': 1,
'[': 1,
']': 1,
'=': 2,
'\n': 0,
}
for ch, expected_backslash_count in expected_backslash_counts.items():
expected = '{}{}'.format('\\' * expected_backslash_count, ch)
actual = _get_drawtext_text_repr(ch)
assert expected == actual
#def test_version():
# subprocess.check_call(['ffmpeg', '-version'])