001    /*
002     * Copyright (C) 2010 The Guava Authors
003     *
004     * Licensed under the Apache License, Version 2.0 (the "License");
005     * you may not use this file except in compliance with the License.
006     * You may obtain a copy of the License at
007     *
008     * http://www.apache.org/licenses/LICENSE-2.0
009     *
010     * Unless required by applicable law or agreed to in writing, software
011     * distributed under the License is distributed on an "AS IS" BASIS,
012     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
013     * See the License for the specific language governing permissions and
014     * limitations under the License.
015     */
016    
017    package com.google.common.base;
018    
019    import com.google.common.annotations.Beta;
020    import com.google.common.annotations.GwtCompatible;
021    
022    /**
023     * Static methods pertaining to ASCII characters (those in the range of values
024     * {@code 0x00} through {@code 0x7F}), and to strings containing such
025     * characters.
026     *
027     * <p>ASCII utilities also exist in other classes of this package:
028     * <ul>
029     * <li>{@link Charsets#US_ASCII} specifies the {@code Charset} of ASCII characters.
030     * <li>{@link CharMatcher#ASCII} matches ASCII characters and provides text processing methods
031     *     which operate only on the ASCII characters of a string.
032     * </ul>
033     *
034     * @author Craig Berry
035     * @author Gregory Kick
036     * @since 7
037     */
038    @GwtCompatible
039    public final class Ascii {
040    
041      private Ascii() {}
042    
043      /* The ASCII control characters, per RFC 20. */
044      /**
045       * Null ('\0'): The all-zeros character which may serve to accomplish
046       * time fill and media fill.  Normally used as a C string terminator.
047       * <p>Although RFC 20 names this as "Null", note that it is distinct
048       * from the C/C++ "NULL" pointer.
049       *
050       * @since 8
051       */
052      public static final byte NUL = 0;
053    
054      /**
055       * Start of Heading: A communication control character used at
056       * the beginning of a sequence of characters which constitute a
057       * machine-sensible address or routing information.  Such a sequence is
058       * referred to as the "heading."  An STX character has the effect of
059       * terminating a heading.
060       *
061       * @since 8
062       */
063      public static final byte SOH = 1;
064    
065      /**
066       * Start of Text: A communication control character which
067       * precedes a sequence of characters that is to be treated as an entity
068       * and entirely transmitted through to the ultimate destination.  Such a
069       * sequence is referred to as "text."  STX may be used to terminate a
070       * sequence of characters started by SOH.
071       *
072       * @since 8
073       */
074      public static final byte STX = 2;
075    
076      /**
077       * End of Text: A communication control character used to
078       * terminate a sequence of characters started with STX and transmitted
079       * as an entity.
080       *
081       * @since 8
082       */
083      public static final byte ETX = 3;
084    
085      /**
086       * End of Transmission: A communication control character used
087       * to indicate the conclusion of a transmission, which may have
088       * contained one or more texts and any associated headings.
089       *
090       * @since 8
091       */
092      public static final byte EOT = 4;
093    
094      /**
095       * Enquiry: A communication control character used in data
096       * communication systems as a request for a response from a remote
097       * station.  It may be used as a "Who Are You" (WRU) to obtain
098       * identification, or may be used to obtain station status, or both.
099       *
100       * @since 8
101       */
102      public static final byte ENQ = 5;
103    
104      /**
105       * Acknowledge: A communication control character transmitted
106       * by a receiver as an affirmative response to a sender.
107       *
108       * @since 8
109       */
110      public static final byte ACK = 6;
111    
112      /**
113       * Bell ('\a'): A character for use when there is a need to call for
114       * human attention.  It may control alarm or attention devices.
115       *
116       * @since 8
117       */
118      public static final byte BEL = 7;
119    
120      /**
121       * Backspace ('\b'): A format effector which controls the movement of
122       * the printing position one printing space backward on the same
123       * printing line.  (Applicable also to display devices.)
124       *
125       * @since 8
126       */
127      public static final byte BS = 8;
128    
129      /**
130       * Horizontal Tabulation ('\t'): A format effector which controls the
131       * movement of the printing position to the next in a series of
132       * predetermined positions along the printing line.  (Applicable also to
133       * display devices and the skip function on punched cards.)
134       *
135       * @since 8
136       */
137      public static final byte HT = 9;
138    
139      /**
140       * Line Feed ('\n'): A format effector which controls the movement of
141       * the printing position to the next printing line.  (Applicable also to
142       * display devices.) Where appropriate, this character may have the
143       * meaning "New Line" (NL), a format effector which controls the
144       * movement of the printing point to the first printing position on the
145       * next printing line.  Use of this convention requires agreement
146       * between sender and recipient of data.
147       *
148       * @since 8
149       */
150      public static final byte LF = 10;
151    
152      /**
153       * Alternate name for {@link #LF}.  ({@code LF} is preferred.)
154       *
155       * @since 8
156       */
157      public static final byte NL = 10;
158    
159      /**
160       * Vertical Tabulation ('\v'): A format effector which controls the
161       * movement of the printing position to the next in a series of
162       * predetermined printing lines.  (Applicable also to display devices.)
163       *
164       * @since 8
165       */
166      public static final byte VT = 11;
167    
168      /**
169       * Form Feed ('\f'): A format effector which controls the movement of
170       * the printing position to the first pre-determined printing line on
171       * the next form or page.  (Applicable also to display devices.)
172       *
173       * @since 8
174       */
175      public static final byte FF = 12;
176    
177      /**
178       * Carriage Return ('\r'): A format effector which controls the
179       * movement of the printing position to the first printing position on
180       * the same printing line.  (Applicable also to display devices.)
181       *
182       * @since 8
183       */
184      public static final byte CR = 13;
185    
186      /**
187       * Shift Out: A control character indicating that the code
188       * combinations which follow shall be interpreted as outside of the
189       * character set of the standard code table until a Shift In character
190       * is reached.
191       *
192       * @since 8
193       */
194      public static final byte SO = 14;
195    
196      /**
197       * Shift In: A control character indicating that the code
198       * combinations which follow shall be interpreted according to the
199       * standard code table.
200       *
201       * @since 8
202       */
203      public static final byte SI = 15;
204    
205      /**
206       * Data Link Escape: A communication control character which
207       * will change the meaning of a limited number of contiguously following
208       * characters.  It is used exclusively to provide supplementary controls
209       * in data communication networks.
210       *
211       * @since 8
212       */
213      public static final byte DLE = 16;
214    
215      /**
216       * Device Controls: Characters for the control
217       * of ancillary devices associated with data processing or
218       * telecommunication systems, more especially switching devices "on" or
219       * "off."  (If a single "stop" control is required to interrupt or turn
220       * off ancillary devices, DC4 is the preferred assignment.)
221       *
222       * @since 8
223       */
224      public static final byte DC1 = 17; // aka XON
225    
226      /**
227       * Transmission on/off: Although originally defined as DC1, this ASCII
228       * control character is now better known as the XON code used for software
229       * flow control in serial communications.  The main use is restarting
230       * the transmission after the communication has been stopped by the XOFF
231       * control code.
232       *
233       * @since 8
234       */
235      public static final byte XON = 17; // aka DC1
236    
237      /**
238       * @see #DC1
239       *
240       * @since 8
241       */
242      public static final byte DC2 = 18;
243    
244      /**
245       * @see #DC1
246       *
247       * @since 8
248       */
249      public static final byte DC3 = 19; // aka XOFF
250    
251      /**
252       * Transmission off. @see #XON
253       *
254       * @since 8
255       */
256      public static final byte XOFF = 19; // aka DC3
257    
258      /**
259       * @see #DC1
260       *
261       * @since 8
262       */
263      public static final byte DC4 = 20;
264    
265      /**
266       * Negative Acknowledge: A communication control character
267       * transmitted by a receiver as a negative response to the sender.
268       *
269       * @since 8
270       */
271      public static final byte NAK = 21;
272    
273      /**
274       * Synchronous Idle: A communication control character used by
275       * a synchronous transmission system in the absence of any other
276       * character to provide a signal from which synchronism may be achieved
277       * or retained.
278       *
279       * @since 8
280       */
281      public static final byte SYN = 22;
282    
283      /**
284       * End of Transmission Block: A communication control character
285       * used to indicate the end of a block of data for communication
286       * purposes.  ETB is used for blocking data where the block structure is
287       * not necessarily related to the processing format.
288       *
289       * @since 8
290       */
291      public static final byte ETB = 23;
292    
293      /**
294       * Cancel: A control character used to indicate that the data
295       * with which it is sent is in error or is to be disregarded.
296       *
297       * @since 8
298       */
299      public static final byte CAN = 24;
300    
301      /**
302       * End of Medium: A control character associated with the sent
303       * data which may be used to identify the physical end of the medium, or
304       * the end of the used, or wanted, portion of information recorded on a
305       * medium.  (The position of this character does not necessarily
306       * correspond to the physical end of the medium.)
307       *
308       * @since 8
309       */
310      public static final byte EM = 25;
311    
312      /**
313       * Substitute: A character that may be substituted for a
314       * character which is determined to be invalid or in error.
315       *
316       * @since 8
317       */
318      public static final byte SUB = 26;
319    
320      /**
321       * Escape: A control character intended to provide code
322       * extension (supplementary characters) in general information
323       * interchange.  The Escape character itself is a prefix affecting the
324       * interpretation of a limited number of contiguously following
325       * characters.
326       *
327       * @since 8
328       */
329      public static final byte ESC = 27;
330    
331      /**
332       * File/Group/Record/Unit Separator: These information separators may be
333       * used within data in optional fashion, except that their hierarchical
334       * relationship shall be: FS is the most inclusive, then GS, then RS,
335       * and US is least inclusive.  (The content and length of a File, Group,
336       * Record, or Unit are not specified.)
337       *
338       * @since 8
339       */
340      public static final byte FS = 28;
341    
342      /**
343       * @see #FS
344       *
345       * @since 8
346       */
347      public static final byte GS = 29;
348    
349      /**
350       * @see #FS
351       *
352       * @since 8
353       */
354      public static final byte RS = 30;
355    
356      /**
357       * @see #FS
358       *
359       * @since 8
360       */
361      public static final byte US = 31;
362    
363      /**
364       * Space: A normally non-printing graphic character used to
365       * separate words.  It is also a format effector which controls the
366       * movement of the printing position, one printing position forward.
367       * (Applicable also to display devices.)
368       *
369       * @since 8
370       */
371      public static final byte SP = 32;
372    
373      /**
374       * Alternate name for {@link #SP}.
375       *
376       * @since 8
377       */
378      public static final byte SPACE = 32;
379    
380      /**
381       * Delete: This character is used primarily to "erase" or
382       * "obliterate" erroneous or unwanted characters in perforated tape.
383       *
384       * @since 8
385       */
386      public static final byte DEL = 127;
387    
388      /**
389       * The minimum value of an ASCII character.
390       *
391       * @since 9
392       */
393      @Beta
394      public static final int MIN = 0;
395    
396      /**
397       * The maximum value of an ASCII character.
398       *
399       * @since 9
400       */
401      @Beta
402      public static final int MAX = 127;
403    
404      /**
405       * Returns a copy of the input string in which all {@linkplain #isUpperCase(char) uppercase ASCII
406       * characters} have been converted to lowercase. All other characters are copied without
407       * modification.
408       */
409      public static String toLowerCase(String string) {
410        int length = string.length();
411        StringBuilder builder = new StringBuilder(length);
412        for (int i = 0; i < length; i++) {
413          builder.append(toLowerCase(string.charAt(i)));
414        }
415        return builder.toString();
416      }
417    
418      /**
419       * If the argument is an {@linkplain #isUpperCase(char) uppercase ASCII character} returns the
420       * lowercase equivalent. Otherwise returns the argument.
421       */
422      public static char toLowerCase(char c) {
423        return isUpperCase(c) ? (char) (c ^ 0x20) : c;
424      }
425    
426      /**
427       * Returns a copy of the input string in which all {@linkplain #isLowerCase(char) lowercase ASCII
428       * characters} have been converted to uppercase. All other characters are copied without
429       * modification.
430       */
431      public static String toUpperCase(String string) {
432        int length = string.length();
433        StringBuilder builder = new StringBuilder(length);
434        for (int i = 0; i < length; i++) {
435          builder.append(toUpperCase(string.charAt(i)));
436        }
437        return builder.toString();
438      }
439    
440      /**
441       * If the argument is a {@linkplain #isLowerCase(char) lowercase ASCII character} returns the
442       * uppercase equivalent. Otherwise returns the argument.
443       */
444      public static char toUpperCase(char c) {
445        return isLowerCase(c) ? (char) (c & 0x5f) : c;
446      }
447    
448      /**
449       * Indicates whether {@code c} is one of the twenty-six lowercase ASCII alphabetic characters
450       * between {@code 'a'} and {@code 'z'} inclusive. All others (including non-ASCII characters)
451       * return {@code false}.
452       */
453      public static boolean isLowerCase(char c) {
454        return (c >= 'a') && (c <= 'z');
455      }
456    
457      /**
458       * Indicates whether {@code c} is one of the twenty-six uppercase ASCII alphabetic characters
459       * between {@code 'A'} and {@code 'Z'} inclusive. All others (including non-ASCII characters)
460       * return {@code false}.
461       */
462      public static boolean isUpperCase(char c) {
463        return (c >= 'A') && (c <= 'Z');
464      }
465    }