/// <summary>
/// 寻找字符的位置信息
/// </summary>
/// <param name="KeyWord"></param>
/// <param name="root"></param>
/// <returns></returns>
public static List <LocAndValue <String> > FindWordLoc(string KeyWord, MyRootHtmlNode root)
{
var paragrahIdList = new List <LocAndValue <String> >();
foreach (var paragrah in root.Children)
{
//从各个段落的内容中取得：内容包含了内置列表，所以，这里不再重复
foreach (var contentNode in paragrah.Children)
{
if (contentNode.TableId == -1)
{
var Idx = contentNode.Content.IndexOf(KeyWord);
if (Idx != -1)
{
var Loc = new LocAndValue <String>()
{
Value = KeyWord,
Loc = contentNode.PositionId,
StartIdx = Idx,
};
paragrahIdList.Add(Loc);
}
}
}
}
return(paragrahIdList);
}
bool JiaFangValidator(LocAndValue <string> x)
{
if (x.Value.Contains("招标"))
{
return(false);
}
return(true);
}
static bool IsMatch <T>(WordRule rule, LocAndValue <T> evaluate)
{
if (rule.Description != null && rule.Description.Count != 0)
{
if (!rule.Description.Contains(evaluate.Description))
{
return(false);
}
}
if (rule.Word != null && rule.Word.Count != 0)
{
if (!rule.Word.Contains(evaluate.Value.ToString()))
{
return(false);
}
}
return(true);
}
/// <summary>
/// 距离（别的词语在后面，则为正数）
/// </summary>
/// <param name="other"></param>
/// <returns></returns>
public int Distance(LocAndValue <T> other)
{
int mypos = Loc * 1000 + StartIdx;
int otherpos = other.Loc * 1000 + other.StartIdx;
if (Value is string)
{
//别的词语在后面，则为正数
if (other.StartIdx > this.StartIdx)
{
//其他
return(otherpos - mypos - Value.ToString().Length);
}
else
{
return(otherpos + other.Value.ToString().Length - mypos);
}
}
else
{
//别的词语在后面，则为正数
return(otherpos - mypos);
}
}
/// <summary>
/// 正则表达式检索方法(前置，正则，后置)
/// </summary>
/// <param name="loc"></param>
/// <param name="OrgString"></param>
/// <param name="regularfeature"></param>
/// <param name="SplitChar"></param>
/// <returns></returns>
public static List <LocAndValue <String> > RegularExFinder(int loc, string OrgString, struRegularExpressFeature regularfeature, string SplitChar = "")
{
var list = new List <LocAndValue <String> >();
var reglist = RegularTool.GetRegular(OrgString, regularfeature.RegularExpress);
foreach (var reg in reglist)
{
//根据前后词语进行过滤
bool IsBeforeOK = true;
string BeforeString = "";
if (regularfeature.LeadingWordList != null)
{
IsBeforeOK = false;
//前置词语
foreach (var leading in regularfeature.LeadingWordList)
{
if (reg.Index - leading.Length >= 0)
{
var word = OrgString.Substring(reg.Index - leading.Length, leading.Length);
if (word.Equals(leading))
{
BeforeString = leading;
IsBeforeOK = true;
break;
}
else
{
continue;
}
}
}
}
if (!IsBeforeOK)
{
continue;
}
bool IsAfterOK = true;
string AfterString = "";
if (regularfeature.TrailingWordList != null)
{
IsAfterOK = false;
//后置词语
foreach (var trailing in regularfeature.TrailingWordList)
{
if (reg.Index + reg.Length + trailing.Length <= OrgString.Length)
{
var word = OrgString.Substring(reg.Index + reg.Length, trailing.Length);
if (word.Equals(trailing))
{
AfterString = trailing;
IsAfterOK = true;
break;
}
else
{
continue;
}
}
}
}
if (IsBeforeOK && IsAfterOK)
{
var Loc = new LocAndValue <String>()
{
Value = BeforeString + SplitChar + reg.RawData + SplitChar + AfterString,
StartIdx = reg.Index - BeforeString.Length,
Loc = loc
};
list.Add(Loc);
}
}
return(list);
}
