一旦超过某个宽度，就沿空格断开字符串（Python）
我正在基础图像上渲染文本 一个核心要求是，每当字符的总宽度超过基本图像的宽度时，字符串都要换行到下一行。我通过以下正确工作的代码段来实现这一点：一旦超过某个宽度，就沿空格断开字符串（Python）,python,word-wrap,Python,Word Wrap,我正在基础图像上渲染文本 一个核心要求是，每当字符的总宽度超过基本图像的宽度时，字符串都要换行到下一行。我通过以下正确工作的代码段来实现这一点： base_width, base_height = base_img.size font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", font_size) line_width = 0 line_count = 1 lines = [] string =
base_width, base_height = base_img.size
font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", font_size)
line_width = 0
line_count = 1
lines = []
string = ""
for c in text:
line_width += font.getsize(c)[0]
string+=str(c)
if line_width > base_width:
lines.append(string)
string = ""
line_width = 0
line_count += 1
if string:
lines.append(string)
行lorem ipsum行=['lorem ip'，'sum']行=['lorem'，'ipsum']行=['lorem'，'ipsum']In [1]: import textwrap
In [2]: textwrap.wrap('x lorem ipsum', width=5)
Out[2]: ['x', 'lorem', 'ipsum']
TextWrapper#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import textwrap
class MyTextWrapper(textwrap.TextWrapper):
def _split(self, text):
assert isinstance(text, StringWithWidth)
return [StringWithWidth(i) for i in super()._split(text._str)]
def _wrap_chunks(self, chunks):
# only modify ''.join in the original code
"""_wrap_chunks(chunks : [string]) -> [string]
Wrap a sequence of text chunks and return a list of lines of
length 'self.width' or less. (If 'break_long_words' is false,
some lines may be longer than this.) Chunks correspond roughly
to words and the whitespace between them: each chunk is
indivisible (modulo 'break_long_words'), but a line break can
come between any two chunks. Chunks should not have internal
whitespace; ie. a chunk is either all whitespace or a "word".
Whitespace chunks will be removed from the beginning and end of
lines, but apart from that whitespace is preserved.
"""
lines = []
if self.width <= 0:
raise ValueError("invalid width %r (must be > 0)" % self.width)
if self.max_lines is not None:
if self.max_lines > 1:
indent = self.subsequent_indent
else:
indent = self.initial_indent
if len(indent) + len(self.placeholder.lstrip()) > self.width:
raise ValueError("placeholder too large for max width")
# Arrange in reverse order so items can be efficiently popped
# from a stack of chucks.
chunks.reverse()
while chunks:
# Start the list of chunks that will make up the current line.
# cur_len is just the length of all the chunks in cur_line.
cur_line = []
cur_len = 0
# Figure out which static string will prefix this line.
if lines:
indent = self.subsequent_indent
else:
indent = self.initial_indent
# Maximum width for this line.
width = self.width - len(indent)
# First chunk on line is whitespace -- drop it, unless this
# is the very beginning of the text (ie. no lines started yet).
if self.drop_whitespace and chunks[-1].strip() == '' and lines:
del chunks[-1]
while chunks:
l = len(chunks[-1])
# Can at least squeeze this chunk onto the current line.
if cur_len + l <= width:
cur_line.append(chunks.pop())
cur_len += l
# Nope, this line is full.
else:
break
# The current line is full, and the next chunk is too big to
# fit on *any* line (not just this one).
if chunks and len(chunks[-1]) > width:
self._handle_long_word(chunks, cur_line, cur_len, width)
cur_len = sum(map(len, cur_line))
# If the last chunk on this line is all whitespace, drop it.
if self.drop_whitespace and cur_line and cur_line[-1].strip() == '':
cur_len -= len(cur_line[-1])
del cur_line[-1]
if cur_line:
if (self.max_lines is None or
len(lines) + 1 < self.max_lines or
(not chunks or
self.drop_whitespace and
len(chunks) == 1 and
not chunks[0].strip()) and cur_len <= width):
# Convert current line back to a string and store it in
# list of all lines (return value).
lines.append(StringWithWidth(
indent + ''.join(map(_as_str, cur_line))))
else:
while cur_line:
if (cur_line[-1].strip() and
cur_len + len(self.placeholder) <= width):
cur_line.append(self.placeholder)
lines.append(StringWithWidth(
indent + ''.join(map(_as_str, cur_line))))
break
cur_len -= len(cur_line[-1])
del cur_line[-1]
else:
if lines:
prev_line = lines[-1].rstrip()
if (len(prev_line) + len(self.placeholder) <=
self.width):
lines[-1] = prev_line + self.placeholder
break
lines.append(indent + self.placeholder.lstrip())
break
return lines
def _make_str_fwd(name):
def func(self, *args, **kwargs):
return StringWithWidth(getattr(self._str, name)(*args, **kwargs))
func.__name__ = name
return func
def _as_str(val):
if isinstance(val, StringWithWidth):
val = val._str
assert isinstance(val, str)
return val
class StringWithWidth:
char_width = {
'x': 1,
's': 2,
' ': 1
}
def __init__(self, s):
self._str = s
expandtabs = _make_str_fwd('expandtabs')
translate = _make_str_fwd('translate')
strip = _make_str_fwd('strip')
__getitem__ = _make_str_fwd('__getitem__')
def __eq__(self, rhs):
return self._str == _as_str(rhs)
def __add__(self, rhs):
return StringWithWidth(self._str + _as_str(rhs))
def __len__(self):
return sum(map(self.char_width.__getitem__, self._str))
def __repr__(self):
return repr(self._str)
def main():
print(MyTextWrapper(width=8).wrap(StringWithWidth('x ss s')))
if __name__ == '__main__':
main()
#/usr/bin/env蟒蛇3
#-*-编码：utf-8-*-
导入文本包装
类MyTextWrapper（textwrap.TextWrapper）：
def_分割（自身，文本）：
断言isinstance（文本，StringWithWidth）
返回[StringWithWidth（i）for i in super（）。\u split（text.\u str）]
def_wrap_块（self，chunks）：
#仅修改“”。在原始代码中加入
“”“\u wrap\u块（块：[string]）->[string]
换行一系列文本块，并返回一个文本行列表
长度为'self.width'或更小。（如果'break\u long\u words'为假，
有些行可能比这个长。）块大致对应
对于单词及其之间的空格：每个块都是
不可分割（模'break_long_words'），但换行符可以
位于任意两个块之间。块不应具有内部
空白；也就是说，块不是全部空白就是一个“单词”。
将从文件的开头和结尾删除空白块
行，但除此之外，保留空白。
"""
行=[]
如果自宽为1：
缩进=自缩进
其他：
缩进=自初始缩进
如果len（缩进）+len（self.placeholder.lstrip（））>self.width：
raise VALUERROR（“占位符对于最大宽度而言太大”）
#按相反顺序排列，以便有效地弹出项目
#从一堆夹头上。
chunks.reverse（）
而区块：
#开始组成当前行的块列表。
#cur_len就是cur_行中所有块的长度。
cur_line=[]
cur_len=0
#找出哪一个静态字符串将作为此行的前缀。
如果行：
缩进=自缩进
其他：
缩进=自初始缩进
#此行的最大宽度。
宽度=自身宽度-长度（缩进）
#行中的第一个块是空白——删除它，除非
#是课文的开头（即还没有开始行）。
如果self.drop_空格和块[-1].strip（）==''和行：
del块[-1]
而区块：
l=len（块[-1]）
#至少可以将该块压缩到当前行。
如果当前长度+l宽度：
self.\u handle\u long\u word（块、cur\u line、cur\u len、宽度）
cur_len=总和（映射（len，cur_line））
#如果这一行的最后一个区块都是空白，请删除它。
如果self.drop_空格和cur_行以及cur_行[-1]。strip（）=''：
cur_len-=len（cur_线[-1]）
德尔库鲁线[-1]
如果当前线路：
如果（self.max_line）为无或
len（线）+1<自最大线或
（不是块或块）
self.drop_空格和
len（块）==1和
不是chunk[0].strip（））和cur_len尽管我认为递归可能更优雅，但这种简单的方法可能会有所帮助。请注意，字符宽度的固定值需要替换为相应的函数调用
#！蟒蛇3
#编码=utf-8
“换行演示”
text=“lorem ipsum dolor sit amet blablah”
打印（“断开”，文本）
words=text.split（）
宽度=[求和（[5表示w中的c]）表示w中的文字]
#印刷品（字）
#打印（宽度）
印刷品（文字），“文字”）
对于[10,25,55,80100120]中的wmax：
打印（“\n最大线宽：”，wmax）
行=[]
li=0
r=范围（长度（宽度））#0…5
对于r中的i：
w=总和（宽度[li:i+1]）
如果w>=wmax且i>0：
line.append（“.”join（单词[li:i]））
li=i
打印（“--”）
w=总和（宽度[li:i+1]）
打印（“，i，字[i]，宽度[i]，w）
#余数
line.append（“.”join（单词[li:]））
打印（行）
输出：
10
text lorem ipsum dolor sit amet blablah
string lor
split ['lor']
lines ['lor']
string
text lorem ipsum dolor sit amet blablah
string em
split ['em', '']
lines ['lor', 'em']
string
text lorem ipsum dolor sit amet blablah
string ips
split ['ips']
lines ['lor', 'em', 'ips']
string
text lorem ipsum dolor sit amet blablah
string um
split ['um', '']
lines ['lor', 'em', 'ips', 'um']
string
text lorem ipsum dolor sit amet blablah
string dol
split ['dol']
lines ['lor', 'em', 'ips', 'um', 'dol']
string
text lorem ipsum dolor sit amet blablah
string or
split ['or', '']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or']
string
text lorem ipsum dolor sit amet blablah
string sit
split ['sit']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit']
string
text lorem ipsum dolor sit amet blablah
string am
split ['', 'am']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '']
string am
text lorem ipsum dolor sit amet blablah
string ame
split ['ame']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame']
string
text lorem ipsum dolor sit amet blablah
string t b
split ['t', 'b']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't']
string b
text lorem ipsum dolor sit amet blablah
string bla
split ['bla']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla']
string
text lorem ipsum dolor sit amet blablah
string bla
split ['bla']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla', 'bla
string
['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla', 'bla', 'h']
25
text lorem ipsum dolor sit amet blablah
string lorem
split ['lorem', '']
lines ['lorem']
string
text lorem ipsum dolor sit amet blablah
string ipsum
split ['ipsum', '']
lines ['lorem', 'ipsum']
string
text lorem ipsum dolor sit amet blablah
string dolor
split ['dolor', '']
lines ['lorem', 'ipsum', 'dolor']
string
text lorem ipsum dolor sit amet blablah
string sit am
split ['sit', 'am']
lines ['lorem', 'ipsum', 'dolor', 'sit']
string am
text lorem ipsum dolor sit amet blablah
string amet b
split ['amet', 'b']
lines ['lorem', 'ipsum', 'dolor', 'sit', 'amet']
string b
text lorem ipsum dolor sit amet blablah
string blabla
split ['blabla']
lines ['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'blabla']
string
['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'blabla', 'h']
55
text lorem ipsum dolor sit amet blablah
string lorem ipsum
split ['lorem ipsum', '']
lines ['lorem ipsum']
string
text lorem ipsum dolor sit amet blablah
string dolor sit am
split ['dolor sit', 'am']
lines ['lorem ipsum', 'dolor sit']
string am
text lorem ipsum dolor sit amet blablah
string amet blablah
split ['amet', 'blablah']
lines ['lorem ipsum', 'dolor sit', 'amet']
string blablah
['lorem ipsum', 'dolor sit', 'amet', 'blablah']
80
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor
split ['lorem ipsum', 'dolor']
lines ['lorem ipsum']
string dolor
text lorem ipsum dolor sit amet blablah
string dolor sit amet bl
split ['dolor sit amet', 'bl']
lines ['lorem ipsum', 'dolor sit amet']
string bl
['lorem ipsum', 'dolor sit amet', 'blablah']
100
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor sit
split ['lorem ipsum dolor', 'sit']
lines ['lorem ipsum dolor']
string sit
['lorem ipsum dolor', 'sit amet blablah']
120
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor sit ame
split ['lorem ipsum dolor sit', 'ame']
lines ['lorem ipsum dolor sit']
string ame
['lorem ipsum dolor sit', 'amet blablah']
打破知识产权不受欢迎
6个字
最大线宽：10
0洛雷姆25
---
1同侧25
---
2多洛25
---
3坐15 15
---
4 amet 20 20
---
5胡说八道35 35
['lorem'，'ipsum'，'dolor'，'sit'，'amet'，'blablah']
最大线宽：25
0洛雷姆25
---
1同侧25
---
2多洛25
---
3坐15 15
---
4 amet 20 20
---
5胡说八道35 35
['lorem'，'ipsum'，'dolor'，'sit'，'amet'，'blablah']
最大线宽：55
0洛雷姆25
1同侧25 50
---
2多洛25
3坐15 40
10
text lorem ipsum dolor sit amet blablah
string lor
split ['lor']
lines ['lor']
string
text lorem ipsum dolor sit amet blablah
string em
split ['em', '']
lines ['lor', 'em']
string
text lorem ipsum dolor sit amet blablah
string ips
split ['ips']
lines ['lor', 'em', 'ips']
string
text lorem ipsum dolor sit amet blablah
string um
split ['um', '']
lines ['lor', 'em', 'ips', 'um']
string
text lorem ipsum dolor sit amet blablah
string dol
split ['dol']
lines ['lor', 'em', 'ips', 'um', 'dol']
string
text lorem ipsum dolor sit amet blablah
string or
split ['or', '']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or']
string
text lorem ipsum dolor sit amet blablah
string sit
split ['sit']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit']
string
text lorem ipsum dolor sit amet blablah
string am
split ['', 'am']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '']
string am
text lorem ipsum dolor sit amet blablah
string ame
split ['ame']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame']
string
text lorem ipsum dolor sit amet blablah
string t b
split ['t', 'b']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't']
string b
text lorem ipsum dolor sit amet blablah
string bla
split ['bla']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla']
string
text lorem ipsum dolor sit amet blablah
string bla
split ['bla']
lines ['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla', 'bla
string
['lor', 'em', 'ips', 'um', 'dol', 'or', 'sit', '', 'ame', 't', 'bla', 'bla', 'h']
25
text lorem ipsum dolor sit amet blablah
string lorem
split ['lorem', '']
lines ['lorem']
string
text lorem ipsum dolor sit amet blablah
string ipsum
split ['ipsum', '']
lines ['lorem', 'ipsum']
string
text lorem ipsum dolor sit amet blablah
string dolor
split ['dolor', '']
lines ['lorem', 'ipsum', 'dolor']
string
text lorem ipsum dolor sit amet blablah
string sit am
split ['sit', 'am']
lines ['lorem', 'ipsum', 'dolor', 'sit']
string am
text lorem ipsum dolor sit amet blablah
string amet b
split ['amet', 'b']
lines ['lorem', 'ipsum', 'dolor', 'sit', 'amet']
string b
text lorem ipsum dolor sit amet blablah
string blabla
split ['blabla']
lines ['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'blabla']
string
['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'blabla', 'h']
55
text lorem ipsum dolor sit amet blablah
string lorem ipsum
split ['lorem ipsum', '']
lines ['lorem ipsum']
string
text lorem ipsum dolor sit amet blablah
string dolor sit am
split ['dolor sit', 'am']
lines ['lorem ipsum', 'dolor sit']
string am
text lorem ipsum dolor sit amet blablah
string amet blablah
split ['amet', 'blablah']
lines ['lorem ipsum', 'dolor sit', 'amet']
string blablah
['lorem ipsum', 'dolor sit', 'amet', 'blablah']
80
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor
split ['lorem ipsum', 'dolor']
lines ['lorem ipsum']
string dolor
text lorem ipsum dolor sit amet blablah
string dolor sit amet bl
split ['dolor sit amet', 'bl']
lines ['lorem ipsum', 'dolor sit amet']
string bl
['lorem ipsum', 'dolor sit amet', 'blablah']
100
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor sit
split ['lorem ipsum dolor', 'sit']
lines ['lorem ipsum dolor']
string sit
['lorem ipsum dolor', 'sit amet blablah']
120
text lorem ipsum dolor sit amet blablah
string lorem ipsum dolor sit ame
split ['lorem ipsum dolor sit', 'ame']
lines ['lorem ipsum dolor sit']
string ame
['lorem ipsum dolor sit', 'amet blablah']
def break_lines(img, text, font_size):
base_width = img.size[0]
font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", font_size)
line = ""
lines = []
width_of_line = 0
number_of_lines = 0
# break string into multi-lines that fit base_width
for token in text.split():
token = token+' '
token_width = font.getsize(token)[0]
if width_of_line+token_width < base_width:
line+=token
width_of_line+=token_width
else:
lines.append(line)
number_of_lines += 1
width_of_line = 0
line = ""
line+=token
width_of_line+=token_width
if line:
lines.append(line)
number_of_lines += 1
return lines, number_of_lines
#!python3
#coding=utf-8
""" Line break demo 3 """
def charwidth(char):
return 5
def stringwidth(string):
return sum( [charwidth(char) for char in string] )
text = "lorem ipsum dolor sit amet blablah"
limit = 60
words = text.split()
lines = [[]]
while( words ):
word = words.pop(0)
if stringwidth( " ".join(lines[-1]) ) + 1 + stringwidth(word) < limit:
lines[-1].append(word)
else:
lines.append( [word] )
print( [" ".join(words) for words in lines ] )
def text_width(text, font):
return font.getsize(text)[0]
# Set max_lines to 0 for no limit
def wrap_text(text, font, max_width, max_lines=0):
words = text.split()
lines = []
while(words):
word = words.pop(0)
# Append word if it's not too long
if len(lines) > 0 and (text_width(" ".join(lines[-1]), font) + 1 + text_width(word,font)) < max_width:
lines[-1].append(word)
else:
# Brute-force: chunkify word until it fits
chunk = len(word)
while chunk > 0:
while (text_width(word[:chunk],font) > max_width and chunk > 1):
chunk -= 1
lines.append( [word[:chunk]] )
word = word[chunk:]
chunk = len(word)
lines = [" ".join(words) for words in lines]
if max_lines and len(lines) > max_lines:
lines[max_lines-1] = lines[max_lines-1][:-1] + "..."
return "\n".join(lines[:max_lines])