Question

I am dynamically editing a regex for matching text in a pdf, which can contain hyphenation at the end of some lines.

Example:

Source string:

"consecuti?vely"

Replace rules:

 .Replace("cuti?",@"cuti?(-\s+)?")
 .Replace("con",@"con(-\s+)?")
 .Replace("consecu",@"consecu(-\s+)?")

Desired output:

"con(-\s+)?secu(-\s+)?ti?(-\s+)?vely"

The replace rules are built dynamically, this is just an example which causes problems.

Whats the best solution to perform such a multiple replace, which will produce the desired output?

So far I thought about using Regex.Replace and zipping the word to replace with optional (-\s+)? between each character, but that would not work, because the word to replace already contains special-meaning characters in regex context.

EDIT: My current code, doesnt work when replace rules overlap like in example above

private string ModifyRegexToAcceptHyphensOfCurrentPage(string regex, int searchedPage)
    {
        var originalTextOfThePage = mPagesNotModified[searchedPage];
        var hyphenatedParts = Regex.Matches(originalTextOfThePage, @"\w+\-\s");
        for (int i = 0; i < hyphenatedParts.Count; i++)
        {
            var partBeforeHyphen = String.Concat(hyphenatedParts[i].Value.TakeWhile(c => c != '-'));

            regex = regex.Replace(partBeforeHyphen, partBeforeHyphen + @"(-\s+)?");
        }
        return regex;
    }

Answer 1

I had to give up an easy solution and did the editing of the regex myself. As a side effect, the new approach goes only twice trough the string.

private string ModifyRegexToAcceptHyphensOfCurrentPage(string regex, int searchedPage)
    {
        var indexesToInsertPossibleHyphenation = GetPossibleHyphenPositions(regex, searchedPage);
        var hyphenationToken = @"(-\s+)?";
        return InsertStringTokenInAllPositions(regex, indexesToInsertPossibleHyphenation, hyphenationToken);
    }

    private static string InsertStringTokenInAllPositions(string sourceString, List<int> insertionIndexes, string insertionToken)
    {
        if (insertionIndexes == null || string.IsNullOrEmpty(insertionToken)) return sourceString;

        var sb = new StringBuilder(sourceString.Length + insertionIndexes.Count * insertionToken.Length);
        var linkedInsertionPositions = new LinkedList<int>(insertionIndexes.Distinct().OrderBy(x => x));
        for (int i = 0; i < sourceString.Length; i++)
        {
            if (!linkedInsertionPositions.Any())
            {
                sb.Append(sourceString.Substring(i));
                break;
            }
            if (i == linkedInsertionPositions.First.Value)
            {
                sb.Append(insertionToken);
            }
            if (i >= linkedInsertionPositions.First.Value)
            {
                linkedInsertionPositions.RemoveFirst();
            }
            sb.Append(sourceString[i]);
        }
        return sb.ToString();
    }

    private List<int> GetPossibleHyphenPositions(string regex, int searchedPage)
    {
        var originalTextOfThePage = mPagesNotModified[searchedPage];
        var hyphenatedParts = Regex.Matches(originalTextOfThePage, @"\w+\-\s");
        var indexesToInsertPossibleHyphenation = new List<int>();
        //....
        // Aho-Corasick to find all occurences of all 
        //strings in "hyphenatedParts" in the "regex" string
        // ....
        return indexesToInsertPossibleHyphenation;
    }