C# PdfReader.TextFromPage方法代碼示例

        /// <summary>
        /// Reads the the run date of this report from the first page of data (page 2).
        /// </summary>
        /// <returns>The run date if it is found, otherwise null</returns>
        DateTime? readReportDate(PdfReader reader)
        {
            DateTime reportDate = DateTime.MinValue;

            var text = reader.TextFromPage(2);

            if (FieldPatterns.RunDate.IsMatch(text))
            {
                DateTime.TryParse(FieldPatterns.RunDate.Match(text).Groups[1].Value.Trim(), out reportDate);
            }

            if (reportDate != DateTime.MinValue)
                return reportDate;
            else
                return null;
        }

        /// <summary>
        /// Reads the Bargaining Unit information on the first page of the report.
        /// </summary>
        /// <returns>A collection BargainingUnit objects for this report.</returns>
        IEnumerable<BargainingUnit> readBargainingUnits(PdfReader reader)
        {
            string replace = " ";
            var units = new List<BargainingUnit>();
            //the Fire BU is never output as a code in the BU table?
            var text = reader.TextFromPage(1).Replace("Fire ", "FIR ");
            //get all the BU chunks
            var chunks = getPageChunks(text).Where(c => FieldPatterns.BargainingUnit.IsMatch(c));

            foreach (var chunk in chunks)
            {
                //get each of the BUs in this chunk
                var matches = FieldPatterns.BargainingUnit.Matches(chunk);
                //split the chunk at the BU code points (leaving their names)
                var names = FieldPatterns.BargainingUnit.Split(chunk)
                                                        .Where(s => !String.IsNullOrEmpty(s.Trim()))
                                                        .Select(s => FieldPatterns.ConsecutiveSpaces.Replace(s, replace).Trim());
                for (int i = 0; i < matches.Count; i++)
                {
                    var match = matches[i];
                    //there will probably be chunks containing BU codes that were already processed
                    if(!units.Any(bu => bu.Code == match.Value))
                        units.Add(new BargainingUnit() { Code = match.Value, Name = names.ElementAt(i) });
                }
            }

            bargainingUnits = units.ToDictionary(bu => bu.Code, bu => bu);

            return units;
        }

        /// <summary>
        /// Interprets the fiscal year from the first page of this report.
        /// </summary>
        /// <returns>A complete FiscalYear object, or null if it cannot be read.</returns>
        FiscalYear readFiscalYear(PdfReader reader)
        {
            FiscalYear fiscalYear = null;

            var text = reader.TextFromPage(1);

            if (FieldPatterns.FiscalYear.IsMatch(text))
            {
                var match = FieldPatterns.FiscalYear.Match(text);
                fiscalYear = new FiscalYear(match.Groups[1].Value, match.Groups[2].Value);
            }

            return fiscalYear;
        }

 /// <summary>
 /// Private implementation that acts on an open PdfReader.
 /// </summary>
 private IEnumerable<IEnumerable<string>> getAlignmentCorrectedClassData(PdfReader reader)
 {
     return
         Enumerable.Range(2, reader.NumberOfPages - 1)
                   .Select(n => reader.TextFromPage(n))
                   .Select(page => getPageChunks(page))
                   .Select(chunks => fixAlignment(chunks))
                   .ToArray();
 }