from charfinder import UnicodeNameIndex
TEMPLATE_NAME = 'http_charfinder.html'
CONTENT_TYPE = 'text/html; charset=UTF-8'
SAMPLE_WORDS = ('bismillah chess cat circled Malayalam digit'
' Roman face Ethiopic black mark symbol dot'
' operator Braille hexagram').split()
ROW_TPL = '<tr><td>{code_str}</td><th>{char}</th><td>{name}</td></tr>'
LINK_TPL = '<a href="/?query={0}" title="find "{0}"">{0}</a>'
LINKS_HTML = ', '.join(LINK_TPL.format(word) for word in
sorted(SAMPLE_WORDS, key=str.upper))
index = UnicodeNameIndex()
with open(TEMPLATE_NAME) as tpl:
template = tpl.read()
template = template.replace('{links}', LINKS_HTML)
# BEGIN HTTP_CHARFINDER_HOME
def home(request): # <1>
query = request.GET.get('query', '').strip() # <2>
print('Query: {!r}'.format(query)) # <3>
if query: # <4>
descriptions = list(index.find_descriptions(query))
res = '\n'.join(ROW_TPL.format(**descr._asdict())
for descr in descriptions)
msg = index.status(query, len(descriptions))
else:
descriptions = []
def test_index():
sample_index = UnicodeNameIndex(sample_chars)
assert len(sample_index) == 9
def sample_index():
return UnicodeNameIndex(sample_chars)
def load_index():
import time
global index
index = UnicodeNameIndex()
time.sleep(2)
def full_index():
return UnicodeNameIndex()
def test_find_word_match_2():
result = UnicodeNameIndex().find_chars('sign')
assert result.items[:2] == ['#', '$']
def test_find_description_match_2():
result = UnicodeNameIndex().find_descriptions('sign', 1, 3)
result = list(result)
assert result[0].char == '$'
assert result[1].char == '%'
def test_find_word_match_1():
result = UnicodeNameIndex().find_chars('chess black')
assert result.count == 6
def test_find_no_word_match():
result = UnicodeNameIndex().find_chars('kdjshfkjsd')
assert result.count == 0
def test_index():
index = UnicodeNameIndex().index
assert len(index) > 10000
DESCRIPTION:
implementation and comments of code 18-14
quite not sure with TCP server usage
"""
import sys
import asyncio
# should import charfinder from https://github.com/fluentpython/example-code/blob/master/18-asyncio/charfinder/charfinder.py
from charfinder import UnicodeNameIndex # UnicodeNameIndex: 문자명 인덱스 생성, 쿼리 메서드 제공
CRLF = b'\r\n'
PROMPT = b'?> '
index = UnicodeNameIndex(
) # 객체 생성할 떄 기존 charfinder_index.pickle이 있으면 사용, 없으면 인덱스 빌드 -> 수초 소
@asyncio.coroutine
def handle_queries(reader, writer): # 서버에 전달할 코루틴
while True: # 제어문자 올때 까지 무한 루프
writer.write(PROMPT) # not coroutine
yield from writer.drain() # is coroutine
data = yield from reader.readline() # is coroutine
try:
query = data.decode().strip()
except UnicodeDecodeError:
query = '\x00' # null, 간편함을 위한 트릭
import asyncio
import sys
from charfinder import UnicodeNameIndex # 用于构建名称索引，提供查询方法
CRLF = b'\r\n'
PROMPT = b'?> '
index = UnicodeNameIndex(
) # 实例化 UnicodeNameIndex 类时，会使用 charfinder_index.pickle 文件(如果存在)，或者构建这个文件，因此第一次运行时要等几秒钟服务器才会启动
async def handle_queries(
reader, writer
): # 这个协程要传给 asyncio.start_server 函数，接收的两个参数是 asyncio.StreamReader 对象和 asyncio.StreamWriter 对象
while True: # 循环处理会话，直到从客户端接收到控制字符后退出
writer.write(PROMPT) # StreamWriter.write 方法不是协程，只是普通函数；这行代码发送 ?> 提示符
await writer.drain() # StreamWriter.drain 方法刷新 writer 缓冲，是协程
data = await reader.readline(
) # StreamReader.readline 方法是协程，返回一个 bytes 对象
try:
query = data.decode().strip() # 默认编码 utf8
except UnicodeDecodeError:
query = '\x00'
client = writer.get_extra_info('peername') # 返回与套接字连接的远程地址
print('Received from {}: {!r}'.format(client, query)) # 在服务器控制台中记录查询
if query:
if ord(query[:1]) < 32:
break # 如果收到控制字符或空字符，退出循环
lines = list(
index.find_description_strs(query)