Search Chinese Through First Letter of Pinyin

[aleegreat]

Could you add this feature：search chinese through first letter of Pinyin??

*Thanks Very Much*

[admin]

Sure, right after I've learned Chinese.

[bdeshi]

a forum user who knows chinese/pinyin can probably write a converter. It's basically just a [complicated-rule-based] replace operation, right?

[fankyo]

This AutoHotkey code looks short, so it shouldn't be difficult?

"我们可以看到从16" => "WMKYKDC16"

Code: Select all

#Requires AutoHotkey >=2.0

a:=zh2py("我们可以看到从16") ; 输出“EJHZ -> N”
MsgBox a
Return

; 从 php 转换而来的 (http://www.sjyhome.com/php/201311170606.html)
zh2py(str)
{
	; 根据汉字区位表,(http://www.mytju.com/classcode/tools/QuWeiMa_FullList.asp)
	; 我们可以看到从16-55区之间是按拼音字母排序的,所以我们只需要判断某个汉字的区位码就可以得知它的拼音首字母.

	; 区位表第一部份,按拼音字母排序的.
	; 16区-55区
	/*
		'A'=>0xB0A1, 'B'=>0xB0C5, 'C'=>0xB2C1, 'D'=>0xB4EE, 'E'=>0xB6EA, 'F'=>0xB7A2, 'G'=>0xB8C1,'H'=>0xB9FE,
		'J'=>0xBBF7, 'K'=>0xBFA6, 'L'=>0xC0AC, 'M'=>0xC2E8, 'N'=>0xC4C3, 'O'=>0xC5B6, 'P'=>0xC5BE,'Q'=>0xC6DA,
		'R'=>0xC8BB, 'S'=>0xC8F6, 'T'=>0xCBFA, 'W'=>0xCDDA, 'X'=>0xCEF4, 'Y'=>0xD1B9, 'Z'=>0xD4D1
	*/
	static FirstTable  := [ 0xB0C5, 0xB2C1, 0xB4EE, 0xB6EA, 0xB7A2, 0xB8C1, 0xB9FE, 0xBBF7, 0xBFA6, 0xC0AC, 0xC2E8
	                      , 0xC4C3, 0xC5B6, 0xC5BE, 0xC6DA, 0xC8BB, 0xC8F6, 0xCBFA, 0xCDDA, 0xCEF4, 0xD1B9, 0xD4D1, 0xD7FA ]
	static FirstLetter := StrSplit("ABCDEFGHJKLMNOPQRSTWXYZ")

	; 区位表第二部份,不规则的,下面的字母是每个区里面对应字的拼音首字母.从网上查询整理出来的,可能会有部份错误.
	; 56区-87区
	static SecondTable := [ StrSplit("CJWGNSPGCGNEGYPBTYYZDXYKYGTZJNMJQMBSGZSCYJSYYFPGKBZGYDYWJKGKLJSWKPJQHYJWRDZLSYMRYPYWWCCKZNKYYG")
	                      , StrSplit("TTNGJEYKKZYTCJNMCYLQLYPYSFQRPZSLWBTGKJFYXJWZLTBNCXJJJJTXDTTSQZYCDXXHGCKBPHFFSSTYBGMXLPBYLLBHLX")
	                      , StrSplit("SMZMYJHSOJNGHDZQYKLGJHSGQZHXQGKXZZWYSCSCJXYEYXADZPMDSSMZJZQJYZCJJFWQJBDZBXGZNZCPWHWXHQKMWFBPBY")
	                      , StrSplit("DTJZZKXHYLYGXFPTYJYYZPSZLFCHMQSHGMXXSXJYQDCSBBQBEFSJYHWWGZKPYLQBGLDLCDTNMAYDDKSSNGYCSGXLYZAYPN")
	                      , StrSplit("PTSDKDYLHGYMYLCXPYCJNDQJWXQXFYYFJLEJPZRXCCQWQQSBZKYMGPLBMJRQCFLNYMYQMSQYRBCJTHZTQFRXQHXMQJCJLY")
	                      , StrSplit("QGJMSHZKBSWYEMYLTXFSYDXWLYCJQXSJNQBSCTYHBFTDCYZDJWYGHQFRXWCKQKXEBPTLPXJZSRMEBWHJLBJSLYYSMDXLCL")
	                      , StrSplit("QKXLHXJRZJMFQHXHWYWSBHTRXXGLHQHFNMGYKLDYXZPYLGGSMTCFBAJJZYLJTYANJGBJPLQGSZYQYAXBKYSECJSZNSLYZH")
	                      , StrSplit("ZXLZCGHPXZHZNYTDSBCJKDLZAYFFYDLEBBGQYZKXGLDNDNYSKJSHDLYXBCGHXYPKDJMMZNGMMCLGWZSZXZJFZNMLZZTHCS")
	                      , StrSplit("YDBDLLSCDDNLKJYKJSYCJLKWHQASDKNHCSGAGHDAASHTCPLCPQYBSZMPJLPCJOQLCDHJJYSPRCHNWJNLHLYYQYYWZPTCZG")
	                      , StrSplit("WWMZFFJQQQQYXACLBHKDJXDGMMYDJXZLLSYGXGKJRYWZWYCLZMSSJZLDBYDCFCXYHLXCHYZJQSQQAGMNYXPFRKSSBJLYXY")
	                      , StrSplit("SYGLNSCMHCWWMNZJJLXXHCHSYZSTTXRYCYXBYHCSMXJSZNPWGPXXTAYBGAJCXLYXDCCWZOCWKCCSBNHCPDYZNFCYYTYCKX")
	                      , StrSplit("KYBSQKKYTQQXFCMCHCYKELZQBSQYJQCCLMTHSYWHMKTLKJLYCXWHEQQHTQKZPQSQSCFYMMDMGBWHWLGSLLYSDLMLXPTHMJ")
	                      , StrSplit("HWLJZYHZJXKTXJLHXRSWLWZJCBXMHZQXSDZPSGFCSGLSXYMJSHXPJXWMYQKSMYPLRTHBXFTPMHYXLCHLHLZYLXGSSSSTCL")
	                      , StrSplit("SLDCLRPBHZHXYYFHBMGDMYCNQQWLQHJJCYWJZYEJJDHPBLQXTQKWHLCHQXAGTLXLJXMSLJHTZKZJECXJCJNMFBYCSFYWYB")
	                      , StrSplit("JZGNYSDZSQYRSLJPCLPWXSDWEJBJCBCNAYTWGMPAPCLYQPCLZXSBNMSGGFNZJJBZSFZYNTXHPLQKZCZWALSBCZJXSYZGWK")
	                      , StrSplit("YPSGXFZFCDKHJGXTLQFSGDSLQWZKXTMHSBGZMJZRGLYJBPMLMSXLZJQQHZYJCZYDJWFMJKLDDPMJEGXYHYLXHLQYQHKYCW")
	                      , StrSplit("CJMYYXNATJHYCCXZPCQLBZWWYTWBQCMLPMYRJCCCXFPZNZZLJPLXXYZTZLGDLTCKLYRZZGQTTJHHHJLJAXFGFJZSLCFDQZ")
	                      , StrSplit("LCLGJDJZSNZLLJPJQDCCLCJXMYZFTSXGCGSBRZXJQQCTZHGYQTJQQLZXJYLYLBCYAMCSTYLPDJBYREGKLZYZHLYSZQLZNW")
	                      , StrSplit("CZCLLWJQJJJKDGJZOLBBZPPGLGHTGZXYGHZMYCNQSYCYHBHGXKAMTXYXNBSKYZZGJZLQJTFCJXDYGJQJJPMGWGJJJPKQSB")
	                      , StrSplit("GBMMCJSSCLPQPDXCDYYKYPCJDDYYGYWRHJRTGZNYQLDKLJSZZGZQZJGDYKSHPZMTLCPWNJYFYZDJCNMWESCYGLBTZZGMSS")
	                      , StrSplit("LLYXYSXXBSJSBBSGGHFJLYPMZJNLYYWDQSHZXTYYWHMCYHYWDBXBTLMSYYYFSXJCBDXXLHJHFSSXZQHFZMZCZTQCXZXRTT")
	                      , StrSplit("DJHNRYZQQMTQDMMGNYDXMJGDXCDYZBFFALLZTDLTFXMXQZDNGWQDBDCZJDXBZGSQQDDJCMBKZFFXMKDMDSYYSZCMLJDSYN")
	                      , StrSplit("SPRSKMKMPCKLGTBQTFZSWTFGGLYPLLJZHGJJGYPZLTCSMCNBTJBQFKDHBYZGKPBBYMTDSSXTBNPDKLEYCJNYCDYKZTDHQH")
	                      , StrSplit("SYZSCTARLLTKZLGECLLKJLQJAQNBDKKGHPJTZQKSECSHALQFMMGJNLYJBBTMLYZXDXJPLDLPCQDHZYCBZSCZBZMSLJFLKR")
	                      , StrSplit("ZJSNFRGJHXPDHYJYBZGDLQCSEZGXLBLGYXTWMABCHECMWYJYZLLJJYHLGNDJLSLYGKDZPZXJYYZLWCXSZFGWYYDLYHCLJS")
	                      , StrSplit("CMBJHBLYZLYCBLYDPDQYSXQZBYTDKYXJYYCNRJMPDJGKLCLJBCTBJDDBBLBLCZQRPYXJCJLZCSHLTOLJNMDDDLNGKATHQH")
	                      , StrSplit("JHYKHEZNMSHRPHQQJCHGMFPRXHJGDYCHGHLYRZQLCYQJNZSQTKQJYMSZSWLCFQQQXYFGGYPTQWLMCRNFKKFSYYLQBMQAMM")
	                      , StrSplit("MYXCTPSHCPTXXZZSMPHPSHMCLMLDQFYQXSZYJDJJZZHQPDSZGLSTJBCKBXYQZJSGPSXQZQZRQTBDKYXZKHHGFLBCSMDLDG")
	                      , StrSplit("DZDBLZYYCXNNCSYBZBFGLZZXSWMSCCMQNJQSBDQSJTXXMBLTXZCLZSHZCXRQJGJYLXZFJPHYMZQQYDFQJJLZZNZJCDGZYG")
	                      , StrSplit("CTXMZYSCTLKPHTXHTLBJXJLXSCDQXCBBTJFQZFSLTJBTKQBXXJJLJCHCZDBZJDCZJDCPRNPQCJPFCZLCLZXZDMXMPHJSGZ")
	                      , StrSplit("GSZZQLYLWTJPFSYASMCJBTZYYCWMYTZSJJLJCQLWZMALBXYFBPNLSFHTGJWEJJXXGLLJSTGSHJQLZFKCGNNNSZFDEQFHBS")
	                      , StrSplit("AQTGYLBXMMYGSZLDYDQMJJRGBJTKGDHGKBLQKBDMBYLXWCXYTTYBKMRTJZXQJBHLMHMJJZMQASLDCYXYQDLQCAFYWYXQHZ") ]


	static var := Buffer(2)
	
	; 如果不包含中文字符，则直接返回原字符
	if !RegExMatch(str, "[^\x{00}-\x{ff}]")
		Return str
	
	Loop Parse str
	{
		StrPut(A_LoopField, var, "CP936")
		H := NumGet(var, 0, "UChar")
		L := NumGet(var, 1, "UChar")
		
		; 字符集非法
		if (H < 0xB0 || L < 0xA1 || H > 0xF7 || L = 0xFF)
		{
			newStr .= A_LoopField
			Continue
		}
		
		if (H < 0xD8) || (H >= 0xB0 && H <=0xD7) ; 查询文字在一级汉字区(16-55)
		{
			W := (H << 8) | L
			For key, value in FirstTable
			{
				if (W < value)
				{
					newStr .= FirstLetter[key]
					Break
				}
			}
		}
		else ; if (H >= 0xD8 && H <= 0xF7) ; 查询中文在二级汉字区(56-87)
			newStr .= SecondTable[ H - 0xD8 + 1 ][ L - 0xA1 + 1 ]
	}
	
	Return newStr
}

https://www.autohotkey.com/boards/viewt ... 90#p534390