blockreplace/blorp.py at main · mlimper/blockreplace · 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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
#!/usr/bin/python3

import os
import shutil

from argparse import ArgumentParser
from pathlib import Path


# #############################################################################
# argument parsing
# #############################################################################

parser = ArgumentParser()

parser.add_argument("-i", "--inputDirectory",  help="input directory",  default=".")
parser.add_argument("-b", "--blockDirectory",  help="directory with block files",  default=".")
parser.add_argument("-o", "--outputDirectory", help="output directory", default="out")
parser.add_argument("-d", "--delete_output_first", help="if specified, content of the output directory will be deleted (cleaned up) before processing", action="store_true")

pArgs    = parser.parse_args()
argsDict = vars(pArgs)

inputDirectory  = argsDict["inputDirectory"]
blockDirectory  = argsDict["blockDirectory"]
outputDirectory = argsDict["outputDirectory"]
cleanupFirst    = pArgs.delete_output_first


# #############################################################################
# global variables and utility functions
# #############################################################################

BlockFileExt  = ".block"
BlockTagStart = "<blorp>"
BlockTagEnd   = "</blorp>"

def getBlockStr(blockName, blockFiles):
    for bf in blockFiles:
        if bf.stem == blockName:
            with open(bf) as blockFileHandle:
                return blockFileHandle.read()

    errorMsg = "ERROR: Could not replace block \"" + blockName + "\""
    print(errorMsg)
    return "<strong>" + errorMsg + "</strong>"


# #############################################################################
# main script
# #############################################################################

if os.path.exists(outputDirectory):
    if cleanupFirst:
        print("Cleaning up output directory")
        shutil.rmtree(outputDirectory)
    else:
        print("No cleanup flag specified, using output directory as-is.")


htmlFiles  = list(Path(inputDirectory).glob('**/*.html'))
blockFiles = list(Path(blockDirectory).glob('**/*' + BlockFileExt))

print("Collected " + str(len(htmlFiles))  + " HTML input files.")
print("Collected " + str(len(blockFiles)) + " block files.")


outputCnt = 0

for htmlFile in htmlFiles:

    with open(htmlFile) as htmlFileHandle:

        htmlFileContent    = htmlFileHandle.read()
        replacedBlockNames = []
        newHTMLFileContent = htmlFileContent

        blockIdx = htmlFileContent.find(BlockTagStart)

        # parse blocks within the file and replace them
        while blockIdx != -1:
            blockEndIdx = htmlFileContent.find(BlockTagEnd, blockIdx + len(BlockTagStart))

            # very basic error check
            if (blockEndIdx == -1):
                print("ERROR: Incomplete block. Must start with \"" + BlockTagStart +
                      "\" and end with \"" + BlockTagEnd + "\".")
                blockIdx = htmlFileContent.find(BlockTagStart, blockIdx + 1)
                continue

            # parse block name
            blockName = htmlFileContent[blockIdx+len(BlockTagStart):blockEndIdx]

            if blockName in replacedBlockNames:
                blockIdx = htmlFileContent.find(BlockTagStart, blockIdx + 1)
                continue

            fullBlockNew = getBlockStr(blockName, blockFiles)

            # perform replacement for all instances
            fullBlockOld = htmlFileContent[blockIdx:blockEndIdx + len(BlockTagEnd)]
            newHTMLFileContent = newHTMLFileContent.replace(fullBlockOld, fullBlockNew)

            # remember that this block name has been processed for this HTML files
            replacedBlockNames.append(blockName)

            blockIdx = htmlFileContent.find(BlockTagStart, blockIdx + 1)

        # write output file
        inFileDir      = os.path.dirname(htmlFile)
        relDir         = os.path.relpath(inFileDir, inputDirectory)
        outputFilePath = os.path.join(outputDirectory, relDir)

        if not os.path.exists(outputFilePath):
            os.makedirs(outputFilePath)

        outputFile = os.path.join(outputFilePath, os.path.basename(htmlFile))

        with open(outputFile, "w") as htmlOutputFileHandle:
            htmlOutputFileHandle.write(newHTMLFileContent)
            outputCnt += 1

print("Wrote " + str(outputCnt)  + " HTML output files.")