Mal*_*ist 2 c# io parsing text-parsing fileparsing
我正在使用Quickbook的IIF文件格式,我需要编写一个解析器来读取和写入IIF文件,我遇到了一些读取文件的问题.
文件很简单,它们的标签是消除的.每一行都是表定义或行.定义以'!'开头 和表名,行只以表名开头.这是我遇到的问题:一些字段允许换行.
当我第一次遇到这个时,我想,好吧只是按标签而不是逐行解析它,但为了做到这一点,我不得不用标签替换换行符,并且用比列有更多的值,但我伤口带有换行符的值分散在太多列中.
你会如何解析这样的文件？
编辑:一个例子
!CUST NAME REFNUM TIMESTAMP BADDR1 BADDR2 BADDR3 BADDR4 BADDR5 SADDR1 SADDR2 SADDR3 SADDR4 SADDR5 PHONE1 PHONE2 FAXNUM CONT1 CONT2 CTYPE TERMS TAXABLE LIMIT RESALENUM REP TAXITEM NOTEPAD SALUTATION COMPANYNAME FIRSTNAME MIDINIT LASTNAME CUSTFLD1 CUSTFLD2 CUSTFLD3 CUSTFLD4 CUSTFLD5 CUSTFLD6 CUSTFLD7 CUSTFLD8 CUSTFLD9 CUSTFLD10 CUSTFLD11 CUSTFLD12 CUSTFLD13 CUSTFLD14 CUSTFLD15 JOBDESC JOBTYPE JOBSTATUS JOBSTART JOBPROJEND JOBEND HIDDEN DELCOUNT
CUST St. Mark 359 1176670332 Saint Mark Catholic Church 609 W Main St City, State Zip
!CLASS NAME REFNUM TIMESTAMP HIDDEN DELCOUNT
!INVITEM NAME REFNUM TIMESTAMP INVITEMTYPE DESC PURCHASEDESC ACCNT ASSETACCNT COGSACCNT QNTY QNTY PRICE COST TAXABLE PAYMETH TAXVEND TAXDIST PREFVEND REORDERPOINT EXTRA CUSTFLD1 CUSTFLD2 CUSTFLD3 CUSTFLD4 CUSTFLD5 DEP_TYPE ISPASSEDTHRU HIDDEN DELCOUNT USEID
INVITEM Labor 1 1119915308 SERV Labor 0
!TIMEACT DATE JOB EMP ITEM PITEM DURATION PROJ NOTE XFERTOPAYROLL BILLINGSTATUS
TIMEACT 3/8/08 876 Development Jane Doe {Consultant} Labor 00:15 Renewing all domain name for 876 Development.
REIMBURSEMENT: 44.72 for one year renewal on all domain names. N 1
TIMEACT 3/17/08 Greg:Bridge Jane Doe {Consultant} Labor 01:00 Preparing Studio N 1
TIMEACT 3/17/08 John Doe and Associates Jane Doe {Consultant} Labor 00:06 REIMBURSEMENT: Toner cartridge on ebay & Fuser from FastPrinters- ask wendell before invoicing to see if this fixed the problem
49.99 (include tax) toner
$175.18 (include tax) fuser
N 1
TIMEACT 3/17/08 John Doe II Jane Doe {Consultant} Labor 01:00 Fixing Kandis's computer - replaced entire computer with similar system N 1
我做的:
public DataSet parseIIF(Stream file) {
iifSet = new DataSet();
String fileText;
using (StreamReader sr = new StreamReader(file)) {
fileText = sr.ReadToEnd();
}
//replace line breaks with tabs
//fileText.Replace('\n', '\t');
fileText = fileText.Replace("\r\n", "\n");
fileText = fileText.Replace('\r', '\n');
//split along tabs
string[] lines = fileText.Split('\n');
this.createTables(lines, iifSet);
this.fillSet(lines, iifSet);
return iifSet;
}
/// <summary>
/// Reads an array of lines and parses them into tables for the dataset
/// </summary>
/// <param name="lines">String Array of lines from the iif file</param>
/// <param name="iifSet">DataSet to be manipulated</param>
private void fillSet(string[] lines, DataSet set) {
//CODING HORROR
//WARNING: I will monkey with the for loop index, be prepared!
for (int i = 0; i < lines.Length; i++) {
if (this.isTableHeader(lines[i])) {
//ignore this line, tables are alread defined
continue;
}
if (lines[i] == "" || lines[i] == "\r" || lines[i] == "\n\r" || lines[i] == "\n") {
//ignore lines that are empty if not inside a record
//probably the end of the file, it always ends with a blank line break
continue;
}
if (lines[i].IndexOf(";__IMPORTED__") != -1) {
continue;
//just signifying that it's been imported by quickbook's timer before, don't need it
}
string line = lines[i];
while (!isFullLine(line, set)){
i++; //<--------------------------- MONKEYING done here!
line += lines[i];
}
//now, the line should be complete, we can parse it by tabs now
this.parseRecord(line, set);
}
}
private void parseRecord(string line, DataSet set) {
if (isTableHeader(line)) {
//we don't want to deal with headers here
return;
}
String tablename = line.Split('\t')[0];
//this just removes the first value and the line break from the last value
String[] parameters = this.createDataRowParams(line);
//add it to the dataset
set.Tables[tablename].Rows.Add(parameters);
}
private bool isFullLine(string line, DataSet set) {
if (isTableHeader(line)) {
return true; //assumes table headers won't have line breaks
}
int values = line.Split('\t').Length;
string tableName = line.Split('\t')[0];
int columns = set.Tables[tableName].Columns.Count;
if (values < columns) {
return false;
} else {
return true;
}
}
private void createTables(string[] lines, DataSet set) {
for (int index = 0; index < lines.Length; index++) {
if (this.isTableHeader(lines[index])) {
set.Tables.Add(createTable(lines[index]));
}
}
}
private bool isTableHeader(string tab) {
if (tab.StartsWith("!"))
return true;
else
return false;
}
private bool isNewLine(string p) {
if (p.StartsWith("!"))
return true;
if (iifSet.Tables[p.Split('\t')[0]] != null) //that little mess there grabs the first record in the line, sorry about the mess
return true;
return false;
}
private DataTable createTable(string line) {
String[] values = line.Split('\t');
//first value is always the title
//remove the ! from it
values[0] = values[0].Substring(1); //remove the first character
DataTable dt = new DataTable(values[0]);
values[0] = null; //hide first title so it doesn't get used, cheaper than resetting array
foreach (String name in values) {
if (name == null || name == "")
continue;
DataColumn dc = new DataColumn(name, typeof(String));
try {
dt.Columns.Add(dc);
} catch (DuplicateNameException) {
//odd
dc = new DataColumn(name + "_duplicateCol" + dt.Columns.Count.ToString());
dt.Columns.Add(dc);
//if there is a triple, just throw it
}
}
return dt;
}
private string getTableName(string line) {
String[] values = line.Split('\t');
//first value is always the title
if(values[0].StartsWith("!")){
//remove the ! from it
values[0] = values[0].Substring(1); //remove the first character
}
return values[0];
}
private string[] createDataRowParams(string line) {
string[] raw = line.Split('\t');
string[] values = new string[raw.Length - 1];
//copy all values except the first one
for (int i = 0; i < values.Length; i++) {
values[i] = raw[i + 1];
}
//remove last line break from the record
if (values[values.Length - 1].EndsWith("\n")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf('\n'));
} else if (values[values.Length - 1].EndsWith("\n\r")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf("\n\r"));
} else if (values[values.Length - 1].EndsWith("\r")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf('\r'));
}
return values;
}
private string[] createDataRowParams(string line, int max) {
string[] raw = line.Split('\t');
int length = raw.Length - 1;
if (length > max) {
length = max;
}
string[] values = new string[length];
for (int i = 0; i < length; i++) {
values[i] = raw[i + 1];
}
if (values[values.Length - 1].EndsWith("\n")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf('\n'));
} else if (values[values.Length - 1].EndsWith("\n\r")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf("\n\r"));
} else if (values[values.Length - 1].EndsWith("\r")) {
values[values.Length - 1] = values[values.Length - 1].Substring(0, values[values.Length - 1].LastIndexOf('\r'));
}
return values;
}