Use pinyin4j. jar to convert Chinese characters to PinYin

You can use pinyin4j. jar to convert Chinese characters to pinyin. The Code is as follows:

[Java]
View plaincopyprint?

1. Package mainapp;
3. Import net. SourceForge. pinyin4j. pinyinhelper;
4. Import net. SourceForge. pinyin4j. format. hanyupinyincasetype;
5. Import net. SourceForge. pinyin4j. format. hanyupinyinoutputformat;
6. Import net. SourceForge. pinyin4j. format. hanyupinyintonetype;
7. Import net. SourceForge. pinyin4j. format. hanyupinyinvchartype;
8. Import net. SourceForge. pinyin4j. format. Exception. badhanyupinyinoutputformatcombination;
10. Public class testpinyin4j
11. {
12. /**
13. * Convert Chinese characters to full spelling
14. *
15. * @ Param SRC
16. * @ Return string
17. */
18. Public static string getpinyin (string SRC)
19. {
20. Char [] T1 = NULL;
21. T1 = SRC. tochararray ();
22. String [] T2 = new string [t1.length];
23. // Set the output format of Chinese characters and Pinyin
24. Hanyupinyinoutputformat T3 = new hanyupinyinoutputformat ();
25. T3.setcasetype (hanyupinyincasetype. lowercase );
26. T3.settonetype (hanyupinyintonetype. without_tone );
27. T3.setvchartype (hanyupinyinvchartype. with_v );
28. String t4 = "";
29. Int T0 = t1.length;
30. Try
31. {
32. For (INT I = 0; I <t0; I ++)
33. {
34. // Determine whether it can be a Chinese character
35. // System. Out. println (T1 [I]);
36. If (character. tostring (T1 [I]). Matches ("[// u4e00-// u9fa5] + "))
37. {
38. T2 = pinyinhelper. tohanyupinyinstringarray (T1 [I], T3); // save all the Chinese characters to the T2 array.
39. T4 + = t2 [0]; // obtain the first pronunciation of the Chinese character and connect it to the string T4.
40. }
41. Else
42. {
43. // If it is not a Chinese character, indirectly retrieve the character and connect it to the string T4
44. T4 + = character. tostring (T1 [I]);
45. }
46. }
47. }
48. Catch (badhanyupinyinoutputformatcombination E)
49. {
50. E. printstacktrace ();
51. }
52. Return T4;
53. }
55. /**
56. * Extract the first letter of each Chinese Character
57. *
58. * @ Param Str
59. * @ Return string
60. */
61. Public static string getpinyinheadchar (string Str)
62. {
63. String convert = "";
64. For (Int J = 0; j <Str. Length (); j ++)
65. {
66. Char word = Str. charat (j );
67. // Extract the first letter of a Chinese character
68. String [] pinyinarray = pinyinhelper. tohanyupinyinstringarray (Word );
69. If (pinyinarray! = NULL)
70. {
71. Convert + = pinyinarray [0]. charat (0 );
72. }
73. Else
74. {
75. Convert + = word;
76. }
77. }
78. Return convert;
79. }
81. /**
82. * Convert a string to an ascii code.
83. *
84. * @ Param cnstr
85. * @ Return string
86. */
87. Public static string getcnascii (string cnstr)
88. {
89. Stringbuffer strbuf = new stringbuffer ();
90. // Convert a string to a byte sequence
91. Byte [] bgbk = cnstr. getbytes ();
92. For (INT I = 0; I <bgbk. length; I ++)
93. {
94. // Convert each character to an ascii code
95. Strbuf. append (integer. tohexstring (bgbk [I] & 0xff ));
96. }
97. Return strbuf. tostring ();
98. }
100. Public static void main (string [] ARGs)
101. {
102. String cnstr = "Chen ";
103. System. Out. println (getpinyin (cnstr ));
104. System. Out. println (getpinyinheadchar (cnstr ));
105. System. Out. println (getcnascii (cnstr ));
106. }
107. }

You can search for "pinyin4j. Jar" from the "resource channel" of csdn to find related resources and introduce them to the project.

Pinyin4j can obtain pinyin corresponding to Chinese characters, and its format can be customized.

Features:

1. Support for multiple pinyin systems:

Chinese pinyin
General pinyin
Weishi pinyin
Phonetic transcription
Yali
Mandarin and Rome
2. Support for polyphonic words

The correct pinyin can be obtained based on the context.

3. Support for multiple pinyin formats

Case sensitivity
Supports Unicode U, V, and u
Supports digital tones (lü3), tone symbols (lüs), and non-tone marks (lüs)

From: http://blog.csdn.net/ziwen00/article/details/5436123

You can use pinyin4j. jar to convert Chinese characters to pinyin. The Code is as follows:

[Java]
View plaincopyprint?

1. Package mainapp;
3. Import net. SourceForge. pinyin4j. pinyinhelper;
4. Import net. SourceForge. pinyin4j. format. hanyupinyincasetype;
5. Import net. SourceForge. pinyin4j. format. hanyupinyinoutputformat;
6. Import net. SourceForge. pinyin4j. format. hanyupinyintonetype;
7. Import net. SourceForge. pinyin4j. format. hanyupinyinvchartype;
8. Import net. SourceForge. pinyin4j. format. Exception. badhanyupinyinoutputformatcombination;
10. Public class testpinyin4j
11. {
12. /**
13. * Convert Chinese characters to full spelling
14. *
15. * @ Param SRC
16. * @ Return string
17. */
18. Public static string getpinyin (string SRC)
19. {
20. Char [] T1 = NULL;
21. T1 = SRC. tochararray ();
22. String [] T2 = new string [t1.length];
23. // Set the output format of Chinese characters and Pinyin
24. Hanyupinyinoutputformat T3 = new hanyupinyinoutputformat ();
25. T3.setcasetype (hanyupinyincasetype. lowercase );
26. T3.settonetype (hanyupinyintonetype. without_tone );
27. T3.setvchartype (hanyupinyinvchartype. with_v );
28. String t4 = "";
29. Int T0 = t1.length;
30. Try
31. {
32. For (INT I = 0; I <t0; I ++)
33. {
34. // Determine whether it can be a Chinese character
35. // System. Out. println (T1 [I]);
36. If (character. tostring (T1 [I]). Matches ("[// u4e00-// u9fa5] + "))
37. {
38. T2 = pinyinhelper. tohanyupinyinstringarray (T1 [I], T3); // save all the Chinese characters to the T2 array.
39. T4 + = t2 [0]; // obtain the first pronunciation of the Chinese character and connect it to the string T4.
40. }
41. Else
42. {
43. // If it is not a Chinese character, indirectly retrieve the character and connect it to the string T4
44. T4 + = character. tostring (T1 [I]);
45. }
46. }
47. }
48. Catch (badhanyupinyinoutputformatcombination E)
49. {
50. E. printstacktrace ();
51. }
52. Return T4;
53. }
55. /**
56. * Extract the first letter of each Chinese Character
57. *
58. * @ Param Str
59. * @ Return string
60. */
61. Public static string getpinyinheadchar (string Str)
62. {
63. String convert = "";
64. For (Int J = 0; j <Str. Length (); j ++)
65. {
66. Char word = Str. charat (j );
67. // Extract the first letter of a Chinese character
68. String [] pinyinarray = pinyinhelper. tohanyupinyinstringarray (Word );
69. If (pinyinarray! = NULL)
70. {
71. Convert + = pinyinarray [0]. charat (0 );
72. }
73. Else
74. {
75. Convert + = word;
76. }
77. }
78. Return convert;
79. }
81. /**
82. * Convert a string to an ascii code.
83. *
84. * @ Param cnstr
85. * @ Return string
86. */
87. Public static string getcnascii (string cnstr)
88. {
89. Stringbuffer strbuf = new stringbuffer ();
90. // Convert a string to a byte sequence
91. Byte [] bgbk = cnstr. getbytes ();
92. For (INT I = 0; I <bgbk. length; I ++)
93. {
94. // Convert each character to an ascii code
95. Strbuf. append (integer. tohexstring (bgbk [I] & 0xff ));
96. }
97. Return strbuf. tostring ();
98. }
100. Public static void main (string [] ARGs)
101. {
102. String cnstr = "Chen ";
103. System. Out. println (getpinyin (cnstr ));
104. System. Out. println (getpinyinheadchar (cnstr ));
105. System. Out. println (getcnascii (cnstr ));
106. }
107. }

You can search for "pinyin4j. Jar" from the "resource channel" of csdn to find related resources and introduce them to the project.

Pinyin4j can obtain pinyin corresponding to Chinese characters, and its format can be customized.

Features:

1. Support for multiple pinyin systems:

Chinese pinyin
General pinyin
Weishi pinyin
Phonetic transcription
Yali
Mandarin and Rome
2. Support for polyphonic words

The correct pinyin can be obtained based on the context.

3. Support for multiple pinyin formats

Case sensitivity
Supports Unicode U, V, and u
Supports digital tones (lü3), tone symbols (lüs), and non-tone marks (lüs)

From: http://blog.csdn.net/ziwen00/article/details/5436123