| 1 | #Region "Microsoft.VisualBasic::419efa23219b84576161d08b456aab68, Microsoft.VisualBasic.Core\Text\Paragraph.vb" |
| 2 | |
| 3 | ' Author: |
| 4 | ' |
| 5 | ' asuka (amethyst.asuka@gcmodeller.org) |
| 6 | ' xie (genetics@smrucc.org) |
| 7 | ' xieguigang (xie.guigang@live.com) |
| 8 | ' |
| 9 | ' Copyright (c) 2018 GPL3 Licensed |
| 10 | ' |
| 11 | ' |
| 12 | ' GNU GENERAL PUBLIC LICENSE (GPL3) |
| 13 | ' |
| 14 | ' |
| 15 | ' This program is free software: you can redistribute it and/or modify |
| 16 | ' it under the terms of the GNU General Public License as published by |
| 17 | ' the Free Software Foundation, either version 3 of the License, or |
| 18 | ' (at your option) any later version. |
| 19 | ' |
| 20 | ' This program is distributed in the hope that it will be useful, |
| 21 | ' but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 22 | ' MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 23 | ' GNU General Public License for more details. |
| 24 | ' |
| 25 | ' You should have received a copy of the GNU General Public License |
| 26 | ' along with this program. If not, see <http://www.gnu.org/licenses/>. |
| 27 | |
| 28 | |
| 29 | |
| 30 | ' /********************************************************************************/ |
| 31 | |
| 32 | ' Summaries: |
| 33 | |
| 34 | ' Module Paragraph |
| 35 | ' |
| 36 | ' Function: SplitParagraph, Trim |
| 37 | ' |
| 38 | ' |
| 39 | ' /********************************************************************************/ |
| 40 | |
| 41 | #End Region |
| 42 | |
| 43 | Imports System.Runtime.CompilerServices |
| 44 | Imports Microsoft.VisualBasic.ComponentModel.DataSourceModel |
| 45 | Imports Microsoft.VisualBasic.Language |
| 46 | Imports Microsoft.VisualBasic.Linq |
| 47 | |
| 48 | Namespace Text |
| 49 | |
| 50 | Public Module Paragraph |
| 51 | |
| 52 | ''' <summary> |
| 53 | ''' |
| 54 | ''' </summary> |
| 55 | ''' <param name="text$"></param> |
| 56 | ''' <param name="len%"></param> |
| 57 | ''' <returns></returns> |
| 58 | ''' <remarks> |
| 59 | ''' 假若长度分割落在单词内,则添加一个连接符,假如是空格或者标点符号,则不处理 |
| 60 | ''' </remarks> |
| 61 | <Extension> Public Iterator Function SplitParagraph(text$, len%) As IEnumerable(Of String) |
| 62 | Dim lines$() = text.LineTokens |
| 63 | |
| 64 | For Each i As SeqValue(Of String) In lines.SeqIterator |
| 65 | Dim line$ = +i |
| 66 | Dim s As New Value(Of String) |
| 67 | Dim left% = Scan0 + 1 |
| 68 | |
| 69 | Do While (s = Mid$(line$, left, len)).Length = len |
| 70 | If s.Value.Length = 0 Then |
| 71 | Exit Do ' 已经结束了 |
| 72 | Else |
| 73 | left += len |
| 74 | End If |
| 75 | |
| 76 | Dim nextLine$ = Mid(line, left, len) _ |
| 77 | .Replace(ASCII.TAB, " "c) |
| 78 | Dim part As NamedValue(Of String) = |
| 79 | nextLine.GetTagValue |
| 80 | |
| 81 | If String.IsNullOrEmpty(nextLine) Then |
| 82 | Exit Do |
| 83 | End If |
| 84 | |
| 85 | If Not String.IsNullOrEmpty(part.Name) Then ' 有空格 |
| 86 | s.Value = Trim((+s) & part.Name) |
| 87 | left += part.Name.Length + 1 |
| 88 | ElseIf nextLine.First = " "c Then ' 第一个字符是空格,则忽略掉 |
| 89 | left += 1 |
| 90 | Else |
| 91 | s.Value &= nextLine ' 是剩余的结束部分 |
| 92 | Yield Trim(+s) |
| 93 | s.Value = Nothing ' 必须要value值删除字符串,否则会重复出现最后一行 |
| 94 | Exit Do |
| 95 | End If |
| 96 | |
| 97 | Yield Trim(+s) |
| 98 | Loop |
| 99 | |
| 100 | If Not String.IsNullOrEmpty(+s) Then |
| 101 | Yield Trim(+s) |
| 102 | Else |
| 103 | If i.i <> lines.Length - 1 Then |
| 104 | Yield vbCrLf |
| 105 | End If |
| 106 | End If |
| 107 | Next |
| 108 | End Function |
| 109 | |
| 110 | <MethodImpl(MethodImplOptions.AggressiveInlining)> |
| 111 | Private Function Trim(s$) As String |
| 112 | If s Is Nothing Then |
| 113 | Return "" |
| 114 | Else |
| 115 | Return s.Trim(" ", ASCII.TAB) |
| 116 | End If |
| 117 | End Function |
| 118 | End Module |
| 119 | End Namespace |