使用 python 将 csv 转换为 xml 文件

Question

I am trying to read csv file and convert to xml file using python version 3.8. I didn't get the proper solution after referring the link With PYTHON convert CSV file to XML file . I am appreciating your valuable help and guidelines.

Input CSV file

release,stage,label,jvm_version,os,testunit,testname,testpath
Training,8,MAIN,160_01,Linux,com.java.testunit,com.java.testunit.testcase1,com/sun/ts/tests/client.java
Training,8,MAIN,160_01,Linux,com.java.testunit,com.java.testunit.testcase2,com/sun/ts/tests/client1.java

Tried code and I am not sure, how test-case tag code block. Someone help to improve this code.

import pandas as pd
xml_map = {"test-result": []}
df = pd.read_csv("test.csv", dtype=str, keep_default_na=False, header=0)
print(df.columns)
outfile = open('output.xml', 'w')


def printXML(data, xmlm, level):
    pass


print('<?xml version="1.0"?>', file=outfile)
print('<!DOCTYPE test-log PUBLIC "-//Oracle Corp.//DTD GTLF 1.0//EN" "http://sapphire.us.oracle.com/docs/downloads/gtlf-config-2-0.dtd">', file=outfile)
print(f"""<test-log
      testtype="AUTOMATED"
      release="{df.release.unique()[0]}"
      load="1"
      branch="{df.label.unique()[0]}"
      string="4"
      changenumber="20210303103457"
      analyzer=""
      hostname="adc00isy"
      toptestfile="cts"
      runmodifier=""
      runid="raj_20220411_1">""", file=outfile)
print(f"""
      <environment>
      <env-attribute name="JVM_Version" value="{df.jvm_version.unique()[0]}"/>
      <env-attribute name="Primary_Config" value="w2.jrf"/>
      <env-attribute name="Secondary_Config" value="jrockit80.oracle"/>
      <env-attribute name="OS" value="{df.os.unique()[0]}"/>
      <env-attribute name="RunKey" value="W2K-cts5-appclient-jrockit-load"/>
      <env-attribute name="NativeIO" value="true"/>
      <env-attribute name="JVM_Mode" value="server"/>
      <env-attribute name="JVM_Name" value="jrockit80"/>
      </environment>
      <header-info
      execaccount="bt"
      execdate="2021-03-03 10:34:57.685"
      checksum="7005"
      resultcount="7005"
      harnesstype="cts"
      importinfo="Import from cts"
      testruntype="cts5"/>""", file=outfile)
print("</test-log>", file=outfile)

Expected XML File format

<?xml version="1.0"?>
  <mytest-log
    testtype="MANUAL"
    release="Training"
    branch="MAIN"
  >

  <environment>
    <env-attribute name="jvm_version" value="160_02"/>
    <env-attribute name="os" value="LINUX"/>
  </environment>

  <test-result
    logicalname="java.testunit.testcase1">
    <test-case
      testcasename="java.testunit"
      testunit="java.testunit.testcase1"
      testpath="com/sun/ts/tests/client.java"
    />
    <execution-output>
      <output-details>
      </output-details>
    </execution-output>
  </test-result>
  <test-result
    logicalname="java.testunit.testcase2">
    <test-case
      testcasename="java.testunit"
      testunit="java.testunit.testcase2"
      testpath="com/sun/ts/tests/client1.java"
    />
    <execution-output>
      <output-details>
      </output-details>
    </execution-output>
  </test-result>
</mytest-log>

Answer 1

I have made the following code and working fine now.

from textwrap import indent
import lxml.etree as ET
import pandas as pd
import datetime
import math
import random

df = pd.read_csv("test.csv", dtype=str, keep_default_na=False, header=0)


def random_string():
    digits = range(10)
    random_str = ""
    for _ in range(6):
        index = math.floor(random.random() * 10)
        random_str += str(digits[index])
    return random_str


def generateXML(data):
    datetime_now = datetime.datetime.now()

    root = ET.Element('mytest-log',
                      testtype="AUTOMATED",
                      release=f"{data.release.unique()[0]}",
                      branch=f"{data.label.unique()[0]}",
                      runid=f"AUTO_{random_string()}"
                      )

    envNode = ET.SubElement(root, 'environment')
    envSubNode = ET.SubElement(envNode, 'env-attribute', name='JVM_Version', value=f'{data.jvm_version.unique()[0]}')
    envSubNode = ET.SubElement(envNode, 'env-attribute', {'name': 'OS', 'value': f'{data.os.unique()[0]}'})
 


    for index, row in data[['testunit', 'testname', 'testpath']].iterrows():
        testNode = ET.SubElement(root, 'test-result', {
            "exectime": f"{datetime_now}",
            "result": "FAILURE",
            "isdone": "TRUE")

        testcaseNode = ET.SubElement(testNode, 'test-case', {
            "testcasename": f"{row['testunit']}",
            "testunit": f"{row['testname']}",
            "testpath": f"{row['testpath']}"
        })

    ET.indent(root, space="     ")
    tree_out = ET.tostring(root, pretty_print=True,
                           xml_declaration=True,
                           encoding="UTF-8")
    print(tree_out)
    print('writing into file --> output_lxml.xml')
    with open('output_lxml.xml', 'wb') as file:
        file.write(tree_out)


generateXML(df)