Volian/SourceCode
8
0
Fork 0
Code Issues Pull Requests 1 Projects Releases Wiki Activity
SourceCode/PROMS/DataLoader/TextConvert.cs
Kathy 5c213e8f35
2013-06-21 14:30:25 +00:00

524 lines
20 KiB
C#
Raw Blame History

// ========================================================================
// Copyright 2006 - Volian Enterprises, Inc. All rights reserved.
// Volian Enterprises - Proprietary Information - DO NOT COPY OR DISTRIBUTE
// ------------------------------------------------------------------------
// $Workfile: $ $Revision: $
// $Author: $ $Date: $
//
// $History: $
// ========================================================================
using System;
using System.Collections.Generic;
using System.Text;
using System.Text.RegularExpressions;
using Volian.Base.Library;
namespace DataLoader
{
public static class TextConvert
{
static TextConvert()
{
BuildDictionarySeq();
BuildDictionaryText();
}
private static Dictionary<int, int> dicChar;
public static void BuildDictionarySeq()
{
dicChar = new Dictionary<int, int>();
for (int i = 0; i < 128; i++) dicChar[i] = i;
dicChar[199] = 128; dicChar[252] = 129; dicChar[233] = 130; dicChar[226] = 131;
dicChar[228] = 132; dicChar[224] = 133; dicChar[229] = 134; dicChar[231] = 135;
dicChar[234] = 136; dicChar[235] = 137; dicChar[232] = 138; dicChar[239] = 139;
dicChar[238] = 140; dicChar[236] = 141; dicChar[196] = 142; dicChar[197] = 143;
dicChar[201] = 144; dicChar[230] = 145; dicChar[198] = 146; dicChar[244] = 147;
dicChar[246] = 148; dicChar[242] = 149; dicChar[251] = 150; dicChar[249] = 151;
dicChar[255] = 152; dicChar[214] = 153; dicChar[220] = 154; dicChar[162] = 155;
dicChar[163] = 156; dicChar[165] = 157; dicChar[8359] = 158; dicChar[402] = 159;
dicChar[225] = 160; dicChar[237] = 161; dicChar[243] = 162; dicChar[250] = 163;
dicChar[241] = 164; dicChar[209] = 165; dicChar[170] = 166; dicChar[186] = 167;
dicChar[191] = 168; dicChar[8976] = 169; dicChar[172] = 170; dicChar[189] = 171;
dicChar[188] = 172; dicChar[161] = 173; dicChar[171] = 174; dicChar[187] = 175;
dicChar[9617] = 176; dicChar[9618] = 177; dicChar[9619] = 178; dicChar[9474] = 179;
dicChar[9508] = 180; dicChar[9569] = 181; dicChar[9570] = 182; dicChar[9558] = 183;
dicChar[9557] = 184; dicChar[9571] = 185; dicChar[9553] = 186; dicChar[9559] = 187;
dicChar[9565] = 188; dicChar[9564] = 189; dicChar[9563] = 190; dicChar[9488] = 191;
dicChar[9492] = 192; dicChar[9524] = 193; dicChar[9516] = 194; dicChar[9500] = 195;
dicChar[9472] = 196; dicChar[9532] = 197; dicChar[9566] = 198; dicChar[9567] = 199;
dicChar[9562] = 200; dicChar[9556] = 201; dicChar[9577] = 202; dicChar[9574] = 203;
dicChar[9568] = 204; dicChar[9552] = 205; dicChar[9580] = 206; dicChar[9575] = 207;
dicChar[9576] = 208; dicChar[9572] = 209; dicChar[9573] = 210; dicChar[9561] = 211;
dicChar[9560] = 212; dicChar[9554] = 213; dicChar[9555] = 214; dicChar[9579] = 215;
dicChar[9578] = 216; dicChar[9496] = 217; dicChar[9484] = 218; dicChar[9608] = 219;
dicChar[9604] = 220; dicChar[9612] = 221; dicChar[9616] = 222; dicChar[9600] = 223;
dicChar[945] = 224; dicChar[223] = 225; dicChar[915] = 226; dicChar[960] = 227;
dicChar[931] = 228; dicChar[963] = 229; dicChar[181] = 230; dicChar[964] = 231;
dicChar[934] = 232; dicChar[920] = 233; dicChar[937] = 234; dicChar[948] = 235;
dicChar[8734] = 236; dicChar[966] = 237; dicChar[949] = 238; dicChar[8745] = 239;
dicChar[8801] = 240; dicChar[177] = 241; dicChar[8805] = 242; dicChar[8804] = 243;
dicChar[8992] = 244; dicChar[8993] = 245; dicChar[247] = 246; dicChar[8776] = 247;
dicChar[176] = 248; dicChar[8729] = 249; dicChar[183] = 250; dicChar[8730] = 251;
dicChar[8319] = 252; dicChar[178] = 253; dicChar[9632] = 254; dicChar[160] = 255;
}
public static string ConvertSeq(string s1)
{
Encoding Eibm437 = Encoding.GetEncoding(437);
Encoding Eunicode = Encoding.Unicode;
Decoder d = Eibm437.GetDecoder();
Byte[] bs1 = Eunicode.GetBytes(s1);
Byte[] bs2 = Encoding.Convert(Eunicode, Eibm437, bs1);
char[] cs2 = new char[Eibm437.GetCharCount(bs2)];
for (int i = 0; i < cs2.Length; i++) cs2[i] = (char)bs2[i];
return new string(cs2);
}
public static Regex Reg2;
public static void BuildDictionaryText()
{
dicChar = new Dictionary<int, int>();
dicChar[966] = 216;
dicChar[201] = 274;
dicChar[127] = 916;
dicChar[964] = 947;
dicChar[920] = 952;
dicChar[915] = 961;
dicChar[191] = 964;
dicChar[8801] = 8773;
dicChar[8734] = 8857;
dicChar[7] = 9679;
dicChar[8976] = 9830;
dicChar[9632] = 9604;
//dicChar[236] = 38914;
char[] creg = new char[dicChar.Count];
int i = 0;
foreach (int ic in dicChar.Keys)
{
creg[i] = (char)ic;
i++;
}
Reg2 = new Regex("[" + new string(creg) + "]");
}
public static string ReplaceChars(Match m)
{
char[] cs = m.Value.ToCharArray();
for (int i = 0; i < cs.Length; i++)
{
if (dicChar.ContainsKey((int)(cs[i])))
{
int iKey = (int)cs[i];
int iValue = dicChar[iKey];
cs[i] = (char)iValue;
}
}
return new string(cs);
}
public static string ConvertText(string s1, bool DoCaret)
{
string s2 = s1;
if (DoCaret) s2 = s2.Replace("^", @"\u916");
return ConvertText(s2);
}
private static void ShowRawString(string str, string title)
{
Console.WriteLine("Raw Start --{0}:\n", title);
foreach (char c in str)
{
int ic = (int)c;
if (c != '\n' && (ic > 126 || ic < 32))
Console.Write("<<{0:x4}>>", ic);
else
Console.Write(c);
}
Console.WriteLine("\n-- Raw End:{0}", title);
}
public static string ReplaceUnicode(string s2)
{
return ReplaceUnicode(s2, false);
}
public static string ReplaceUnicode(string s2, bool DoCaret)
{
//char[] tmp;
//tmp = s2.ToCharArray();
string orig = s2;
//ShowRawString(s2, "ReplaceUnicode");
s2 = s2.Replace("`", @"\'b0"); // convert backquote to degree - left over from DOS days.
s2 = s2.Replace("\xa0",@"\u160?"); // hardspace
s2 = s2.Replace("\xb0", @"\'b0"); // degree
s2 = s2.Replace("\x7f", @"\u916?"); // delta
s2 = s2.Replace("\x2265",@"\u8805?"); // greater than or equal
s2 = s2.Replace("\x2264",@"\u8804?"); // less than or equal
s2 = s2.Replace("\xB1",@"\'b1"); // plus minus
s2 = s2.Replace("\x3A3",@"\u931?"); // sigma
s2 = s2.Replace("\x3C4",@"\u947?"); // gamma
s2 = s2.Replace("\xBD",@"\'bd"); // half
s2 = s2.Replace("\x25A0",@"\u9604?"); // accum 2584
s2 = s2.Replace("\x7",@"\u9679?"); // bullet 25CF
s2 = s2.Replace("\x2248",@"\u8776?"); // approx eq
s2 = s2.Replace("\x2261",@"\u8773?"); // similar eq 2245
s2 = s2.Replace("\xF7",@"\'f7"); // division
s2 = s2.Replace("\x221A",@"\u8730?"); // square root
s2 = s2.Replace("\x393",@"\u961?"); // rho 3C1
s2 = s2.Replace("\x3C0",@"\u960?"); // pi
s2 = s2.Replace("\xb5", @"\u956?"); // micro 3BC (try e6, if not work try 109)
s2 = s2.Replace("\x3B4", @"\u948?"); // lower case delta
s2 = s2.Replace("\x3C3", @"\u963?"); // lower case sigma
s2 = s2.Replace("\xBC", @"\'bc"); // quarter
s2 = s2.Replace("\x256A", @"\'d8"); // dist zero, D8
s2 = s2.Replace("\x3C6", @"\'d8"); // dist zero, D8
s2 = s2.Replace("\xC9", @"\u274?"); // energy, 112
s2 = s2.Replace("\xEC", @"\'ec"); // grave
s2 = s2.Replace("\x2502", @"\u9474?"); // bar
s2 = s2.Replace("\x3B5", @"\u949?"); // epsilon
s2 = s2.Replace("\x398", @"\u952?"); // theta, 3B8
s2 = s2.Replace("\x221E", @"\u8857?"); // dot in oval, 2299
s2 = s2.Replace("\xBF", @"\u964?"); // tau, 3C4
s2 = s2.Replace("\x2310", @"\u9830?"); // diamond, 2666
s2 = s2.Replace("\x2192", @"\u8594?");
s2 = s2.Replace("\x2190", @"\u8592?");
s2 = s2.Replace("\x2191", @"\u8593?");
s2 = s2.Replace("\x2193", @"\u8595?");
s2 = s2.Replace("\x2207", @"\u8711?");
s2 = s2.Replace("\x2591", @"\'b0"); // Degree Symbol
s2 = s2.Replace("\xFF", @"\u8593?"); // Up Arrow
s2 = s2.Replace("\xD6", @"\u8595?"); // Down Arrow
if (DoCaret) s2 = s2.Replace("^", @"\u916");
//s2 = s2.Replace("^", @"\u916");
//s2 = ConvertDOSSuperAndSubScripts(s2);
string sBefore = s2;
s2 = ConvertFortranFormatToScienctificNotation(s2);
if (sBefore != s2)
MyGlitches.Add("ConvertFortranFormatToScienctificNotation", sBefore, s2);
// Convert dash to a non-breaking dash. This is a unicode character.
// This character will be used in veproms rather than a dash.
//if the dash is preceeded byte a token remove the space following the token
//#if DEBUG
if (VlnSettings.DebugMode)
{
if (s2.Contains(@"\super "))
Console.WriteLine("RTF Super token");
}
//#endif
s2 = Regex.Replace(s2, @"(\\[^ \\?]*) \-", @"$1\u8209?");
s2 = s2.Replace("-", @"\u8209?");
//Remove spaces between comment end nad Next token
s2 = s2.Replace(@"\v0 \", @"\v0\");
//Change Token Order to match RTB output
s2 = s2.Replace(@"\v0\b0", @"\b0\v0");
s2 = s2.Replace(@"\b0\ulnone", @"\ulnone\b0");
s2 = s2.Replace(@"\par ", "\r\n");
return s2;
}
private static DataLoaderGlitches _MyGlitches;
public static DataLoaderGlitches MyGlitches
{
get
{
if (_MyGlitches == null)
_MyGlitches = new DataLoaderGlitches();
return _MyGlitches;
}
set { _MyGlitches = value; }
}
public static string ConvertFortranFormatToScienctificNotation(string str)
{
// Convert E style numbers to RTF with \super and \nosupersub
string retval = Regex.Replace(str, "([+-]?)([0-9]+)[.]([0-9]*?)0*E([+-]?[0-9]+)", new MatchEvaluator(FixFortranNumber));
return retval;
}
public static string ConvertDOSSuperAndSubScripts(string instr)
{
try
{
string retval = Regex.Replace(instr, "[#](.*?)[#]", "\\up2 $1\\up0 ");// DOS Superscript
retval = Regex.Replace(retval, "[~](.*?)[~]", "\\dn2 $1\\up0 ");// DOS Subscript
return retval;
}
catch (Exception ex)
{
Console.WriteLine("Error in ConvertDOSSuperAndSubScripts");
}
return "";
}
private static string FixFortranNumber(Match match)
{
StringBuilder sb = new StringBuilder(match.Groups[1].Value);
if (match.Groups[3].Length == 0) // Nothing to the right of the decimal
if (match.Groups[2].Value != "1") // Other than "1", multiply it times 10 raised to a power
sb.Append(match.Groups[2].Value + "x10");
else // The number is simply 1 so it can be ignored and 10 can be raised to a power
sb.Append("10");
else // A number with a decimal point
sb.Append(match.Groups[2].Value + "." + match.Groups[3].Value + "x10");
// Add the exponent as superscript
return sb.ToString() + "\\up2 " + match.Groups[4].Value + "\\up0 ";
}
#region CommentedOut
//private static string ConvertFortranFormatToScienctificNotation(string str)
//{
// string outstr = "";
// int orglen = str.Length;
// int cnt = 0;
// int ptr;
// int nbytes;
// int tstr, tstr2, rptr, start = 0;
// while (cnt < orglen)
// {
// // position up to the the next number, sign, or period
// ptr = str.IndexOfAny("+-0123456789.".ToCharArray(), cnt);
// if (ptr == -1)
// {
// outstr += str.Substring(cnt);
// break; // jump out of while loop - nothing else to process
// }
// if ((ptr - cnt) > 0)
// {
// outstr += str.Substring(cnt, ptr - cnt);
// cnt = ptr;
// }
// if (cnt > start && str[cnt - 1] == '\'')
// {
// //B2003-053: only remove the single quote character
// // if str ptr is not at the end of the string or
// // the next char (after the str ptr) is not a space
// // or newline... (as per Paul Linn on 7/17/03)
// int len = orglen - cnt;
// if (len <= 1 || str[cnt + 1] == ' ' || str[cnt + 1] == '\n')
// start = cnt;
// else
// start = cnt - 1;
// }
// else start = cnt;
// tstr = cnt;
// //Skip preceeding signs
// if (str[cnt] == '+' || str[cnt] == '-')
// cnt++;
// cnt = NextNonNumber(str, cnt);
// if ((cnt < str.Length -1) && str[cnt] == '.')
// {
// cnt = NextNonNumber(str, cnt + 1);
// if (str[start] == '\'')
// {
// start++;
// }
// else if ((cnt < str.Length -1) && (str[cnt] == 'E') && (cnt > tstr))
// {
// nbytes = (cnt - tstr); // don't include the 'E'
// outstr += str.Substring(tstr, nbytes);
// cnt++;
// rptr = outstr.Length - 1;
// while (outstr[rptr] == '0') rptr--;
// if (outstr[rptr] != '.') rptr++;
// if (rptr < (outstr.Length - 1))
// outstr = outstr.Substring(0, rptr + 1); // trim trailing 0's
// int poutstr = 0;
// if (outstr[poutstr] == '+' || outstr[poutstr] == '-') poutstr++;
// if (!outstr[poutstr].Equals("1"))
// {
// outstr += "x1";
// }
// outstr += "0\\super ";
// tstr2 = cnt;
// if (str[cnt] == '+' || str[cnt] == '-') cnt++;
// cnt = NextNonNumber(str, cnt);
// if (str[cnt] == '.' && char.IsDigit(str, cnt + 1))
// cnt = NextNonNumber(str, cnt + 1);
// nbytes = cnt - tstr2; // +1;
// outstr += str.Substring(tstr2, nbytes);
// outstr += "\\nosupersub ";
// if (!char.IsLetterOrDigit(str, cnt) && !char.IsWhiteSpace(str, cnt))
// return (str.Substring(tstr));
// }
// else if (cnt > 0)
// {
// outstr += str.Substring(start, cnt - start + ((cnt < str.Length) ? 1 : 0));
// }
// }
// else
// {
// outstr += str.Substring(start, cnt - start + ((cnt < str.Length)?1:0));
// cnt++;
// }
// }
// return (outstr);
//}
//private static int NextNonNumber(string str, int cnt)
//{
// int rtn = 0;
// string tstr = str.Substring(cnt);
// int len = tstr.Length;
// while (rtn < len && char.IsDigit(tstr, rtn)) rtn++;
// return rtn + cnt;
//}
//public static string ConvertDOSSuperAndSubScripts(string instr)
//{
// string outstr = "";
// string tstr = instr;
// int cnt = 0;
// int ptr = 0;
// bool issupper = false, issub = false;
// while (tstr != null && (ptr = tstr.IndexOfAny("#~".ToCharArray(), cnt)) >= 0)
// {
// if (ptr > cnt)
// outstr += tstr.Substring(cnt, ptr - cnt);
// switch (tstr[ptr])
// {
// case '#':
// if (issub || issupper)
// outstr += "\\nosupersub ";
// else
// outstr += "\\super ";
// issupper = !issupper;
// issub = false;
// break;
// case '~':
// if (issupper || issub)
// outstr += "\\nosupersub ";
// else
// outstr += "\\sub ";
// issub = !issub;
// issupper = false;
// break;
// }
// cnt = ptr + 1;
// if (cnt >= tstr.Length)
// tstr = null;
// else
// tstr = instr.Substring(cnt);
// cnt = 0;
// }
// if (tstr != null)
// outstr += tstr;
// return outstr;
//}
#endregion
public static string ConvertText(string s1)
{
string s2 = s1;
//CompareBeforeAndAfter(s1);
s2 = ReplaceUnicode(s2);
// now replace underline on/off (AE,AF), super on/off (C6,C7)
// bold on/off (D5, D6), subscript on/off (D1 A6), and
// italics on/off (B2, DD)
//s2 = s2.Replace("\xAB", "\\ul ");
//s2 = s2.Replace("\xBB", "\\ulnone ");
//s2 = s2.Replace("\x255E", "\\super ");
//s2 = s2.Replace("\x255F", "\\nosupersub ");
//\xAB -> \\ul and \xBB -> \\ulnone - look for pairs:
s2 = Regex.Replace(s2, @"\xAB([^\xBB]*?)\xBB", @"\ul $1\ulnone ");
// if there is an underline on without underline off or vice versa, just remove it.
if (s2.Contains("\xAB") || s2.Contains("\xBB")) s2 = s2.Replace("\xAB", "").Replace("\xBB", "");
s2 = s2.Replace("\x255E", "\\up2 ");
s2 = s2.Replace("\x255F", "\\up0 ");
s2 = s2.Replace("\x2552", "\\b ");
s2 = s2.Replace("\x2553", "\\b0 ");
//s2 = s2.Replace("\x2564", "\\sub ");
//s2 = s2.Replace("\xAA", "\\nosupersub ");
s2 = s2.Replace("\x2564", "\\dn2 ");
s2 = s2.Replace("\xAA", "\\up0 ");
s2 = s2.Replace("\x2593", "\\i ");
s2 = s2.Replace("\x258C", "\\i0 ");
s2 = s2.Replace("\x2559", "\\ul\\b ");
s2 = s2.Replace("\x2558", "\\b0\\ulnone ");
// underline next word is 0x17
// superscript next is 0x18
// subscript next is 0x19
// bold next is 0x13
// if the underline is at beginning of text, don't replace the underline token with a space:
s2 = Regex.Replace(s2, @"^\x17(([A-Za-z0-9]|\\u[0-9]+\?)+)", @"\ul $1\ulnone ");
s2 = Regex.Replace(s2, @"\x17(([A-Za-z0-9]|\\u[0-9]+\?)+)", @" \ul $1\ulnone ");
// \x18([A-Za-z0-9]+)(?:[\x18]|(?= )|\Z|(?=[^A-Za-z0-9]))(.*?)
s2 = Regex.Replace(s2, @"\x18([A-Za-z0-9]+)(?:[\x18]|(?= )|\Z|(?=[^A-Za-z0-9]))(.*?)", @"\up2 $1\up0 $2");
s2 = Regex.Replace(s2, @"\x19([A-Za-z0-9]+)(?:[\x19]|(?= )|\Z|(?=[^A-Za-z0-9]))(.*?)", @"\dn2 $1\up0 $2");
s2 = Regex.Replace(s2, @"\x13([A-Za-z0-9]+)(?:[\x13]|(?= )|\Z|(?=[^A-Za-z0-9]))(.*?)", @"\b $1\b0 $2");
//s2 = Regex.Replace(s2, @"\x18([^\x18 ]*?)(?:[\x18]|(?= )|\Z|/)(.*?)", @"\up2 $1\up0 $2");
//s2 = Regex.Replace(s2, @"\x19([^\x19 ]*?)(?:[\x19]|(?= )|\Z|/)(.*?)", @"\dn2 $1\up0 $2");
//s2 = Regex.Replace(s2, @"\x13([^\x13 ]*?)(?:[\x13]|(?= )|\Z|/)(.*?)", @"\b $1\b0 $2");
s2 = Reg2.Replace(s2, new MatchEvaluator(ReplaceChars));
// Now prepend an escape character, '\', to any curly brace. The curly brace
// is used in rtf land.
s2 = s2.Replace(@"{", @"\{");
s2 = s2.Replace(@"}", @"\}");
s2 = s2.Replace("\n", @"\par "); // line break in tables
s2 = s2.Replace(@"\up0 \up2 ", @"\up2 "); //jsj - 18MAR2010 - rbt.Save() seems to do this automatically
s2 = s2.Replace(@"\up0 \dn2 ", @"\dn2 "); //jsj - 18MAR2010 - rbt.Save() seems to do this automatically
return s2;
}
private static void CompareBeforeAndAfter(string txtBefore)
{
string txtAfter = ConvertSeq(txtBefore);
if (txtAfter != txtBefore)
{
ListDifference(txtBefore, txtAfter);
}
}
private static Dictionary<int, int> _SpecialChars = new Dictionary<int, int>();
private static void ListDifference(string txtBefore, string txtAfter)
{
int nBefore = txtBefore.Length;
int nAfter = txtAfter.Length;
int n = nBefore > nAfter ? nAfter : nBefore;
for (int i = 0; i < n; i++)
{
int chrBefore = (int)(txtBefore[i]);
int chrAfter = (int)(txtAfter[i]);
if (chrBefore != chrAfter)
{
if (_SpecialChars.ContainsKey(chrBefore))
_SpecialChars[chrBefore]++;
else
{
_SpecialChars.Add(chrBefore, 1);
Console.WriteLine("Character Difference 0x{0:X0000} 0x{1:X0000} @ {2}", chrBefore, chrAfter, i);
//Console.WriteLine("Text Difference\r\nBefore '{0}'\r\nAfter '{0}'", txtBefore, txtAfter);
string prefix = i == 0 ? "" : txtBefore.Substring(0, i - 1);
string suffix = i == txtBefore.Length - 1 ? "" : txtBefore.Substring(i + 1);
Console.WriteLine("Found in '{0}' 0x{1:X} '{2}'", prefix, chrBefore, suffix);
}
}
}
if (nBefore != nAfter)
{
Console.WriteLine("Length Difference\r\nBefore '{0}'\r\nAfter '{0}'", txtBefore, txtAfter);
}
}
public static void ListSpecialCharacters()
{
Console.WriteLine("Special Characters");
foreach (int chr in _SpecialChars.Keys)
{
Console.WriteLine("0x{0:X0000} - {1} occurances", chr, _SpecialChars[chr]);
}
}
public static void ResetSpecialCharacters()
{
_SpecialChars = new Dictionary<int, int>();
}
}
}
Reference in New Issue View Git Blame Copy Permalink