我不得不根据你的例子猜测你的makefile结构允许什么,但这应该让你接近:
from pyparsing import *
# elements of the makefile are delimited by line, so we must
# define skippable whitespace to include just spaces and tabs
ParserElement.setDefaultWhitespaceChars(' \t')
NL = LineEnd().suppress()
EQ,COLON,LBRACK,RBRACK = map(Suppress, "=:[]")
identifier = Word(alphas+'_', alphanums)
symbol_assignment = Group(identifier("name") + EQ + empty +
restOfLine("value"))("symbol_assignment")
symbol_ref = Word("$",alphanums+"_.")
def only_column_one(s,l,t):
if col(l,s) != 1:
raise ParseException(s,l,"not in column 1")
# task identifiers have to start in column 1
task_identifier = identifier.copy().setParseAction(only_column_one)
task_description = "des:" + empty + restOfLine("des")
task_path = "path:" + empty + restOfLine("path")
task_para_body = delimitedList(symbol_ref)
task_para = "para:" + LBRACK + task_para_body("para") + RBRACK
task_para.ignore(NL)
task_definition = Group(task_identifier("target") + COLON +
Optional(delimitedList(identifier))("deps") + NL +
(
Optional(task_description + NL) &
Optional(task_path + NL) &
Optional(task_para + NL)
)
)("task_definition")
makefile_parser = ZeroOrMore(
symbol_assignment |
task_definition |
NL
)
if __name__ == "__main__":
test = """\
samtools=/path/to/samtools
picard=/path/to/picard
task1:
des: description
path: /path/to/task1
para: [$global.samtools,
$args.input,
$path
]
task2: task1
"""
# dump out what we parsed, including results names
for element in makefile_parser.parseString(test):
print element.getName()
print element.dump()
print
印刷:
symbol_assignment
['samtools', '/path/to/samtools']
- name: samtools
- value: /path/to/samtools
symbol_assignment
['picard', '/path/to/picard']
- name: picard
- value: /path/to/picard
task_definition
['task1', 'des:', 'description ', 'path:', '/path/to/task1 ', 'para:',
'$global.samtools', '$args.input', '$path']
- des: description
- para: ['$global.samtools', '$args.input', '$path']
- path: /path/to/task1
- target: task1
task_definition
['task2', 'task1']
- deps: ['task1']
- target: task2
dump() 输出显示您可以使用哪些名称来获取已解析元素中的字段,或区分您拥有的元素类型。dump() 是一个方便的通用工具,用于输出 pyparsing 已解析的任何内容。下面是一些更特定于您的特定解析器的代码,展示了如何将字段名称用作点对象引用(element.target
、element.deps
、element.name
等)或 dict 样式引用(element[key]
):
for element in makefile_parser.parseString(test):
if element.getName() == 'task_definition':
print "TASK:", element.target,
if element.deps:
print "DEPS:(" + ','.join(element.deps) + ")"
else:
print
for key in ('des', 'path', 'para'):
if key in element:
print " ", key.upper()+":", element[key]
elif element.getName() == 'symbol_assignment':
print "SYM:", element.name, "->", element.value
印刷:
SYM: samtools -> /path/to/samtools
SYM: picard -> /path/to/picard
TASK: task1
DES: description
PATH: /path/to/task1
PARA: ['$global.samtools', '$args.input', '$path']
TASK: task2 DEPS:(task1)