[英]Parsing text file to tabular data for processing
当前的问题是使用python以表格形式解析特定数据。一小部分数据如下所示
Statistics indicator:0x222235
number of records = 3
records[0]
value one = 2
value two = 5
blocks = 2
block[0] {
some irrelevant data....
value three = 4 bytes
}
block[1]{
some irrelevant data...
value three = 6 bytes
}
records[1]
value one = 3
value two = 5
blocks = 1
block[0] {
some irrelevant data....
value three = 4 bytes
}
records[2]
value one = 7
value two = 6
blocks = 2
block[0] {
some irrelevant data....
value three = 3 bytes
}
block[1]{
some irrelevant data...
value three = 4 bytes
}
Statistics indicator:0x135256
number of records = 2
records[0]
value one = 4
value two = 8
blocks = 1
block[0] {
some irrelevant data....
value three = 6 bytes
}
records[1]
value one = 3
value two = 5
blocks = 1
block[0] {
some irrelevant data....
value three = 3 bytes
}
如图所示,数据具有特定的模式。 它在每个特定数据块的开头都有统计指示器。它具有记录数字段以指示数据块具有的记录数。在每个记录中,``值一''和值二``是不同的。 但是,取决于每个记录具有的块数,有几个“值三”,这些值由“块”字段指示。 这里的问题是将以下数据以表格形式排列,并添加与特定记录相对应的所有值三。
决赛桌应如下所示:
值一值二值三
2 5 10
3 5 4
7 6 7
4 8 6
3 5 3
我正在考虑的方法是先找到“统计指标”,如果找到“统计指标”,我将寻找记录和与每个记录相对应的块的数量,以遍历这些块,然后将值三与对应于相似值一和值二的值相加。 。
这是我尝试提取值一,值二和值三的代码。 我还没有研究求和值三。
import re
import pandas as pd
val_dict = { 'value_one':re.compile(r'value one = (?P<value_one>.*)\n'),
'value_two':re.compile(r'value two = (?P<value_two>.*)\n'),
'value_three':re.compile(r'value three = (?P<value_three>.*)\n')}
def _parse_line(line):
for key, val in val_dict.items():
match = val.search(line)
if match:
return key, match
# if there are no matches
return None, None
def parse_file(filepath):
data = []
with open(filepath, 'r') as file_object:
row = {} # prepare an empty row
for line in file_object:
key, match = _parse_line(line)
# search for keys in the line
if key == 'value_one':
value_one = match.group('value_one')
value_one = int(value_one)
if 'value one' in row: # we always have a full row
data.append(row) # append it to the data liest
row = {} # and reset it
row['value one'] = value_one # we have a match: store the value in row
if key == 'value_two':
value_two = match.group('value_two')
value_two = int(value_two)
if 'value two' in row:
data.append(row)
row = {}
row['value two'] = value_two
if key == 'value_three':
value_three = match.group('value_three')
value_three = int(value_three)
if 'value three' in row:
data.append(row)
row = {}
row['value three'] = value_three
if row != {}: # do not forget the last row
data.append(row)
data = pd.DataFrame(data)
return data
if __name__ == '__main__':
filepath = 'test3.txt'
data = parse_file(filepath)
在这里,也许我们不想使用正则表达式。 但是,如果我们愿意,可以将属性名称设置为左边界,并收集所需的数字,也许使用类似以下的表达式:
value\s+(one|two|three)\s+=\s+([0-9]+)
然后,我们剩下的问题就可以编写脚本了。 如果需要的话,我们还可以在表达式中添加更多边界。
# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"value\s+(one|two|three)\s+=\s+([0-9]+)"
test_str = ("Statistics indicator:0x222235\n\n"
"number of records = 3\n\n"
"records[0]\n\n"
"value one = 2\n\n"
"value two = 5\n\n"
"blocks = 2\n\n"
"block[0] {\n\n"
"some irrelevant data....\n\n"
"value three = 4 bytes\n\n"
"}\n\n"
"block[1]{\n\n"
"some irrelevant data...\n\n"
"value three = 6 bytes\n\n"
"}\n\n"
"records[1]\n\n"
"value one = 3\n\n"
"value two = 5\n\n"
"blocks = 1\n\n"
"block[0] {\n\n"
"some irrelevant data....\n\n"
"value three = 4 bytes\n\n"
"}\n\n"
"records[2]\n\n"
"value one = 7\n\n"
"value two = 6\n\n"
"blocks = 2\n\n"
"block[0] {\n\n"
"some irrelevant data....\n\n"
"value three = 3 bytes\n\n"
"}\n\n"
"block[1]{\n\n"
"some irrelevant data...\n\n"
"value three = 4 bytes\n\n"
"}\n\n"
"Statistics indicator:0x135256\n\n"
"number of records = 2\n\n"
"records[0]\n\n"
"value one = 4\n\n"
"value two = 8\n\n"
"blocks = 1\n\n"
"block[0] {\n\n"
"some irrelevant data....\n\n"
"value three = 6 bytes\n\n"
"}\n\n"
"records[1]\n\n"
"value one = 3\n\n"
"value two = 5\n\n"
"blocks = 1\n\n"
"block[0] {\n\n"
"some irrelevant data....\n\n"
"value three = 3 bytes\n\n"
"}")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
const regex = /value\\s+(one|two|three)\\s+=\\s+([0-9]+)/gm; const str = `Statistics indicator:0x222235 number of records = 3 records[0] value one = 2 value two = 5 blocks = 2 block[0] { some irrelevant data.... value three = 4 bytes } block[1]{ some irrelevant data... value three = 6 bytes } records[1] value one = 3 value two = 5 blocks = 1 block[0] { some irrelevant data.... value three = 4 bytes } records[2] value one = 7 value two = 6 blocks = 2 block[0] { some irrelevant data.... value three = 3 bytes } block[1]{ some irrelevant data... value three = 4 bytes } Statistics indicator:0x135256 number of records = 2 records[0] value one = 4 value two = 8 blocks = 1 block[0] { some irrelevant data.... value three = 6 bytes } records[1] value one = 3 value two = 5 blocks = 1 block[0] { some irrelevant data.... value three = 3 bytes }`; let m; while ((m = regex.exec(str)) !== null) { // This is necessary to avoid infinite loops with zero-width matches if (m.index === regex.lastIndex) { regex.lastIndex++; } // The result can be accessed through the `m`-variable. m.forEach((match, groupIndex) => { console.log(`Found match, group ${groupIndex}: ${match}`); }); }
如果不需要此表达式,则可以在regex101.com中对其进行修改或更改。
jex.im可视化正则表达式:
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.