Python-解析maven依赖树

Question

tree= 
[INFO] +- org.antlr:antlr4:jar:4.7.1:compile
[INFO] |  +- org.antlr:antlr4-runtime:jar:4.7.1:compile
[INFO] |  +- org.antlr:antlr-runtime:jar:3.5.2:compile
[INFO] |  \- com.ibm.icu:icu4j:jar:58.2:compile
[INFO] +- commons-io:commons-io:jar:1.3.2:compile
[INFO] +- brs:dxprog-lang:jar:3.3-SNAPSHOT:compile
[INFO] |  +- brs:libutil:jar:2.51:compile
[INFO] |  |  +- commons-collections:commons-collections:jar:3.2.2:compile
[INFO] |  |  +- org.apache.commons:commons-collections4:jar:4.1:compile
[INFO] |  |  |  +- com.fasterxml.jackson.core:jackson-annotations:jar:2.9.0:compile
    [INFO] |  |  |  \- com.fasterxml.jackson.core:jackson-core:jar:2.9.5:compile
.
.
.


fileObj = open("tree", "r")

for line in fileObj.readlines():
    for word in line.split():
        if "[INFO]" in line.split():
            line = line.replace(line.split().__getitem__(0), "")
            print(line)

            if "|" in line.split():
                line = line.replace(line.split().__getitem__(0), "child")
                print(line)

                if "+-" in line.split() and "|" not in line.split():
                    line = line.replace(line.split().__getitem__(0), "")
                    line = line.replace(line.split().__getitem__(0), "parent")
                    print(line, '\n\n')

 |  |  \- com.google.protobuf:protobuf-java:jar:3.5.1:compile

 child  child  \- com.google.protobuf:protobuf-java:jar:3.5.1:compile

 |  +- com.h2database:h2:jar:1.4.195:compile

 child  +- com.h2database:h2:jar:1.4.195:compile

   parent com.h2database:h2:jar:1.4.195:compile

Answer 1

我不知道你的编程经验是什么，但那不是一个琐碎的任务。

首先，您可以看到依赖项的叠加级别由符号表示。您可以做的最简单的事情是建立一个堆栈,存储从根到chilren,孙子,...的依赖路径：

def build_stack(text):
    stack = []
    for line in text.split("\n"):
        if not line:
            continue

        line = line[7:] # remove [INFO]
        level = line.count("|")
        name = line.split("-", 1)[1].strip() # the part after the -
        stack = stack[:level] + [name] # update the stack: everything up to level-1 and name
        yield stack[:level], name # this is a generator

for bottom_stack, name in build_stack(DATA):
    print (bottom_stack + [name])

输出：

['org.antlr:antlr4:jar:4.7.1:compile']
['org.antlr:antlr4:jar:4.7.1:compile', 'org.antlr:antlr4-runtime:jar:4.7.1:compile']
['org.antlr:antlr4:jar:4.7.1:compile', 'org.antlr:antlr-runtime:jar:3.5.2:compile']
['org.antlr:antlr4:jar:4.7.1:compile', 'com.ibm.icu:icu4j:jar:58.2:compile']
['commons-io:commons-io:jar:1.3.2:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile', 'brs:libutil:jar:2.51:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile', 'brs:libutil:jar:2.51:compile', 'commons-collections:commons-collections:jar:3.2.2:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile', 'brs:libutil:jar:2.51:compile', 'org.apache.commons:commons-collections4:jar:4.1:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile', 'brs:libutil:jar:2.51:compile', 'org.apache.commons:commons-collections4:jar:4.1:compile', 'com.fasterxml.jackson.core:jackson-annotations:jar:2.9.0:compile']
['brs:dxprog-lang:jar:3.3-SNAPSHOT:compile', 'brs:libutil:jar:2.51:compile', 'org.apache.commons:commons-collections4:jar:4.1:compile', 'com.fasterxml.jackson.core:jackson-core:jar:2.9.5:compile']

def create_tree(text):
    tree = {}
    for stack, name in build_stack(text):
        temp = tree
        for n in stack: # find or create...
            temp = temp.setdefault(n, {}) # ...the most inner dict
        temp[name] = {}
    return tree

from pprint import pprint
pprint(create_tree(DATA))

{'brs:dxprog-lang:jar:3.3-SNAPSHOT:compile': {'brs:libutil:jar:2.51:compile': {'commons-collections:commons-collections:jar:3.2.2:compile': {},
                                                                               'org.apache.commons:commons-collections4:jar:4.1:compile': {'com.fasterxml.jackson.core:jackson-annotations:jar:2.9.0:compile': {},
                                                                                                                                           'com.fasterxml.jackson.core:jackson-core:jar:2.9.5:compile': {}}}},
 'commons-io:commons-io:jar:1.3.2:compile': {},
 'org.antlr:antlr4:jar:4.7.1:compile': {'com.ibm.icu:icu4j:jar:58.2:compile': {},
                                        'org.antlr:antlr-runtime:jar:3.5.2:compile': {},
                                        'org.antlr:antlr4-runtime:jar:4.7.1:compile': {}}}
{'brs:dxprog-lang:jar:3.3-SNAPSHOT:compile': {'brs:libutil:jar:2.51:compile': {'commons-collections:commons-collections:jar:3.2.2:compile': {},
                                                                               'org.apache.commons:commons-collections4:jar:4.1:compile': {'com.fasterxml.jackson.core:jackson-annotations:jar:2.9.0:compile': {},
                                                                                                                                           'com.fasterxml.jackson.core:jackson-core:jar:2.9.5:compile': {}}}},
 'commons-io:commons-io:jar:1.3.2:compile': {},
 'org.antlr:antlr4:jar:4.7.1:compile': {'com.ibm.icu:icu4j:jar:58.2:compile': {},
                                        'org.antlr:antlr-runtime:jar:3.5.2:compile': {},
                                        'org.antlr:antlr4-runtime:jar:4.7.1:compile': {}}}

第三，您需要格式化树，即1。提取数据和2。将子级分组到列表中。这是一个简单的树遍历（这里是DFS）：

def format(tree):
    L = []
    for name, subtree in tree.items():
        group, artifact, packaging, version, scope = name.split(":")
        d = {"artifact":artifact} # you can add group, ...
        if subtree: # children are present
            d["children"] = format(subtree)
        L.append(d)
    return L

pprint(format(create_tree(DATA)))

输出：

[{'artifact': 'antlr4',
  'children': [{'artifact': 'antlr4-runtime'},
               {'artifact': 'antlr-runtime'},
               {'artifact': 'icu4j'}]},
 {'artifact': 'commons-io'},
 {'artifact': 'dxprog-lang',
  'children': [{'artifact': 'libutil',
                'children': [{'artifact': 'commons-collections'},
                             {'artifact': 'commons-collections4',
                              'children': [{'artifact': 'jackson-annotations'},
                                           {'artifact': 'jackson-core'}]}]}]}]

你也许可以分组。