gistfile1.py

#Extract data from RAS Geometry files
#@skulk001
########################################################################
import os
import re
import time
import csv
from operator import floordiv

folderLocation = "x:\folderlocation\Models"
listSubFolders = os.listdir(folderLocation)
flowChangeLocationsTable = []
streamGeometry = {}
for subFolder in listSubFolders:
    subFolderPath = folderLocation + "\\" + subFolder
    if os.path.isdir(subFolderPath):
        listSubFolderFiles = os.listdir(subFolderPath)
        for file in listSubFolderFiles:
            #Geometry files in hecras have a ".g0*" extension, the code below filters to look that geometry files only
            if file.find(".g") != -1:
                openFile = open(subFolderPath + "\\" + file, "r")
                readFile= openFile.read()
                #pattern matching to extract specific portion of the file
                pattern2 = re.compile("(?<=\n#Mann=).+(?![A-z]+)")
                pattern3 = re.compile(r"(?<=Type RM Length L Ch R =).+(\d+)")
                manningsCoeff = pattern2.finditer(readFile)
                stations = pattern3.finditer(readFile)
                
                stationsList = []
                for station in stations:
                    if int(station.group().split(",")[0].strip()) == 1:
                        stationsList.append(station.group().split())
                manningsCoeffList = []
                for coeffs in manningsCoeff:
                    numberOfIter = floordiv(int(coeffs.group().split(",")[0])-1, 3) + 1
                    newStartLocation = coeffs.start() + readFile[coeffs.start():].find("\n") + 1
                    TempList = []
                    while numberOfIter > 0:
                        line = readFile[newStartLocation:newStartLocation + readFile[newStartLocation:].find("\n")]
                        newStartLocation = newStartLocation + readFile[newStartLocation:].find("\n") + 1 
                        numberOfIter = numberOfIter - 1
                        for item in line.split():
                            TempList.append(item)
                    manningsCoeffList.append(TempList)
                streamGeometryData = map(list.__add__,stationsList,manningsCoeffList)
                streamGeometry[file] = streamGeometryData

#CSV generation
outputCheckMannings = csv.writer(open(folderLocation + "\\" +'streamGeometry'+ str(time.gmtime().tm_sec) + '.csv', 'wb'))
list = []
for key,value in streamGeometry.items():
    temp = []
    for i in range(len(value)):
        temp1 = []
        temp1.append(key)
        for item in value[i]:
            temp1.append(item)
        temp.append(temp1)
        
    for items in temp:
        finalRow = []
        for item in items:
            for i in item.split(","):
                finalRow.append(i)
        outputCheckMannings.writerow(finalRow)