uscxmlparsepub/xmltester.py at main · cliveleehere/uscxmlparsepub · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
__author__ = 'Clive'

import os
from os import walk

import sqlite3
import xmlhelper
import dbhelper

dbname = "uscdb.db"
xmlpath = r"./xmltest/"

# these are from ustitle.css
aboveSectionLevels = ["title", "subtitle", "chapter", "subchapter", "part", "subpart", "division", "subdivision", "level",
            "appendix", "compiledAct", "courtRules", "courtRule", "reorgnizationPlans", "reorganizationPlan"]

belowSectionLevels = ["subsection", "paragraph", "subparagraph", "clause", "subclause", "item"
                      "subitem", "subsubitem", "level"]

titleNameTable = "titleNames"
titleNameTableFormat = "(_id INTEGER PRIMARY KEY AUTOINCREMENT, titleNumText TEXT, titleName TEXT)"
titleNameTableKeyCol = "titleNumText"

titleChTableSuffix = "ch"
titleSecTableSuffix = "sec"
eachTitleChFormat  = "(_id INTEGER PRIMARY KEY AUTOINCREMENT, ChNo TEXT, ChHeading TEXT, SecStart TEXT, SecEnd TEXT)"
eachTitleSecFormat = "(_id INTEGER PRIMARY KEY AUTOINCREMENT, SecNo TEXT, SecHeading TEXT, SecContent TEXT)"


# hange the current diretory to the xml directory
os.chdir(xmlpath)

# find the path of where the xml files are stored
mypath = os.path.dirname(__file__) + xmlpath

# get all the xml files in the directory
xmlFiles = []
for (dirpath, dirnames, filenames) in walk(mypath):
    for f in filenames:
        froot, fext = os.path.splitext(f)
        if fext == ".xml" or fext == ".xml-bak":
            xmlFiles.append(f)

for f in xmlFiles:
    print ("Testing " + f + "...")
    root = xmlhelper.extract_xml(f, mypath)

    mainroot = root.find('./main/title')
    if mainroot is None:
        mainroot = root.find('./appendix')

    for et in mainroot.iterfind('.//section/content/*'):
        print (et.tag)