Python - tool to a template of THE ONE FILE and insert data from a CSV file

parseCsvToLog.py

#!/usr/bin/python




# NOTE
#   Need to back burner this.  Proving too time consuming to re-create
#   the various attributes from the CSV strings (not enough information)
#   Either need helper from .Net or write this tool in .NET




import getopt
import os
import sys

def Usage():
    print("Usage: %s -t <file> -i <file> -o <file>" % sys.argv[0])
    print("  -t <file>      Template  HTM file")
    print("  -i <file>      Input     CSV file")
    print("  -o <file>      Output    HTM file")


# TODO
def computeTimeStamp(val):
    return "TBD"

# TODO
def computeGroupMemberAttributes(str1, str2, str3):
    str = "TBD"
    if str2 == "Notes":
        str = "isi-group-member=\"{}\" isi-property=\"{}\" isi-text-node=\"\"".format(str1, str2)
    else:
        str = "isi-group-member=\"{}\" isi-property=\"{}\" isi-text-node=\"\"".format(str1, str2)
    return str

TABLE_OPENTAG        = "<table id=\"isi-report\">"
TABLE_CLOSETAG       = "</table>"

CSV_STARTTABLE       = "\"Date Time\""
CSV_ENDTABLE         = "\n\"\""
CSV_BLANK            = "\"\""

def getDataIndexes(contents):
    dataOpenIndex   = contents.find(CSV_STARTTABLE)
    dataCloseIndex  = contents.find(CSV_ENDTABLE, dataOpenIndex)
    return dataOpenIndex, dataCloseIndex 

CSV_START            = "\""
CSV_NEWLINE          = "\n"
CSV_BLANK            = "\"\""

def getGroupInfo(outFp, contents, startIndex, endIndex):
    # assume group data is in form:
    #  "Section Header"
    #  "Section Member"
    #  ...
    #  ""
    index = startIndex
    currentGroup = ""
    while index < endIndex:
        if contents.startswith(CSV_BLANK, index):
            outFp.write("<tr><td></td></tr>\n")
            index += len(CSV_BLANK)
            currentGroup = ""
        elif currentGroup == "" and contents.startswith(CSV_START, index):
            a = index
            index = contents.find(CSV_NEWLINE, index)
            b = index
            str1 = contents[a:b].replace("\"", "")
            str2 = str1.replace(" ", "")
            outFp.write("<tr class=\"sectionHeader\"><td isi-group=\"{}\"\">{}</td></tr>\n".format(str2, str1))
            currentGroup = str2
        elif currentGroup != "" and contents.startswith(CSV_START, index):
            a = index
            index = contents.find(CSV_NEWLINE, index)
            b = index
            str = contents[a:b].replace("\"", "")
            if str.find("=") >= 0:
                parts = contents[a:b].replace("\"", "").split("=")
                str1 = ''.join(parts[0]).strip().replace(" ", "")
                str2 = ''.join(parts[0]).strip()
                str3 = ''.join(parts[1]).strip()
                outFp.write("<tr class=\"sectionMember\"><td isi-group-member=\"{}\" isi-property=\"{}\" isi-text-node=\"\"><span isi-label=\"\">{}</span> = <span isi-value=\"\">{}</span></td></tr>\n".format(currentGroup, str1, str2, str3))
            else:
                parts = contents[a:b].replace("\"", "").split(":")
                str1 = ''.join(parts[0]).strip().replace(" ", "")
                str2 = ''.join(parts[0]).strip()
                str3 = ''.join(parts[1]).strip()
                attrStr = computeGroupMemberAttributes(str1, str2, str3)
                outFp.write("<tr class=\"sectionMember\"><td isi-group-member=\"{}\" {}><span isi-label=\"\">{}</span>: <span isi-value=\"\">{}</span></td></tr>\n".format(currentGroup, attrStr, str1, str2, str3))
        index += 1
    return index

TD_DATA_HEADER = "\"Date Time\""

def getDataAndValues(outFp, contents, startIndex, endIndex):
    # assume first line is headers row
    # and subsequent lines are data rows
    index = startIndex
    while index < endIndex:
        if contents.startswith(TD_DATA_HEADER, index):
            outFp.write("<tr class=\"dataHeader\" isi-data-table=\"\">\n")
            index = contents.find(TD_DATA_HEADER, index)
            a = index
            index = contents.find(CSV_NEWLINE, index)
            b = index
            parts = contents[a:b].replace("\"", "").split(",")
            for part in parts:
                str1 = part.replace(" ", "") #  TODO use lookup
                str2 = part
                outFp.write("<td isi-data-column-header=\"{}\">{}</td></tr>\n".format(str1, str2))
            outFp.write("</tr>\n")
        elif contents.startswith(CSV_START, index):
            index = contents.find(CSV_START, index)
            a = index
            index = contents.find(CSV_NEWLINE, index)
            b = index
            parts = contents[a:b].replace("\"", "").split(",")
            ts = computeTimeStamp(parts[0])
            str = "<tr class=\"data\" isi-data-row=\"\" isi-timestamp=\"{}\"><td class=\"dateTime\">".format(ts)
            idx = 0
            for part in parts:
                str1 = part.replace(" ", "") #  TODO use lookup
                str2 = part
                if idx > 0:
                    str += "<td>"
                idx += 1
                str += "{}</td>".format(str2)
            outFp.write(str + "</tr>\n")
        index += 1

tptFilename  = ''
inFilename   = ''
outFilename  = ''
try:
    # process command arguments
    ouropts, args = getopt.getopt(sys.argv[1:],"t:i:o:h")
    for o, a in ouropts:
        if   o == '-t':
            tptFilename = a
        elif   o == '-i':
            inFilename = a
        elif o == '-o':
            outFilename = a
        elif o == '-h':
            Usage()
            sys.exit(0)
except getopt.GetoptError as e:
    print(str(e))
    Usage()
    sys.exit(2)
 
if type(tptFilename) != str or len(tptFilename) <= 0:
    print("please use -t for input HTM template file")
    Usage()
    sys.exit(0)
if type(inFilename) != str or len(inFilename) <= 0:
    print("please use -i for input CSV log file")
    Usage()
    sys.exit(0)
if type(outFilename) != str or len(outFilename) <= 0:
    print("please use -o for output HTM log file")
    Usage()
    sys.exit(0)

with open(outFilename, 'wb') as outFp:
    with open(tptFilename, 'rb') as tptFp:
        with open(inFilename, 'rb') as inFp:
            tptContents = tptFp.readlines()
            tptContents = ''.join(tptContents)
            contents = inFp.readlines()
            contents = ''.join(contents)

            # get top temlate
            index = tptContents.find(TABLE_OPENTAG)
            outFp.write(tptContents[0:index])

            outFp.write("<table id=\"isi-report\">")
            dataOpenIndex, dataCloseIndex = getDataIndexes(contents)
            index = getGroupInfo(    outFp, contents, 0,              dataOpenIndex)
            index = getDataAndValues(outFp, contents, dataOpenIndex,  dataCloseIndex)
            index = getGroupInfo(   outFp, contents, dataCloseIndex, len(contents)-1)
            outFp.write("</table>")

            # get bottom template
            index = tptContents.find(TABLE_CLOSETAG, index)
            index += len(TABLE_CLOSETAG)
            outFp.write(tptContents[index:-1])