X-Git-Url: https://juplo.de/gitweb/?p=percentcodec;a=blobdiff_plain;f=percentcodec%2Fsrc%2Fmain%2Fjava%2Fde%2Fjuplo%2Fpercentcodec%2FPercentCodec.java;fp=percentcodec%2Fsrc%2Fmain%2Fjava%2Fde%2Fjuplo%2Fpercentcodec%2FPercentCodec.java;h=1a23c097af1ba2c9700aa9484a4e0934931dff6f;hp=0000000000000000000000000000000000000000;hb=a6e0e65cce68acb20abc6ca935471611a740c342;hpb=1d395c6002486d485bde0d5dc713886d70bd3f8a

diff --git a/percentcodec/src/main/java/de/juplo/percentcodec/PercentCodec.java b/percentcodec/src/main/java/de/juplo/percentcodec/PercentCodec.java
new file mode 100644
index 00000000..1a23c097
--- /dev/null
+++ b/percentcodec/src/main/java/de/juplo/percentcodec/PercentCodec.java
@@ -0,0 +1,198 @@
+package de.juplo.percentcodec;
+
+import java.nio.charset.Charset;
+
+/**
+ * This class performes percent-encoding/-decoding like described in RFC 3986.
+ * <p>
+ * Complete URI's are not handled by this implementation.
+ * That is done best with the original {@linkplain java.net.URI}-class from core Java.
+ * The purpose of this class is to have a simple tool to encode/decode the
+ * inner parts of an URI, like a segment of the URI-path (the part between two
+ * forward slashes) or a name or value segment of the query, where all reserved
+ * characters must be encoded/decoded.
+ *
+ * @author kai
+ */
+public class PercentCodec {
+  private final Charset charset;
+
+
+  public PercentCodec(String encoding) {
+    charset = Charset.forName(encoding);
+  }
+
+
+  public String encode(CharSequence in) {
+    StringBuilder out = new StringBuilder();
+    int i = 0;
+    int length = in.length();
+    while (i < length) {
+      int codePoint = Character.codePointAt(in, i);
+      i += Character.charCount(codePoint);
+      switch (codePoint) {
+        case 'a':
+        case 'A':
+        case 'b':
+        case 'B':
+        case 'c':
+        case 'C':
+        case 'd':
+        case 'D':
+        case 'e':
+        case 'E':
+        case 'f':
+        case 'F':
+        case 'g':
+        case 'G':
+        case 'h':
+        case 'H':
+        case 'i':
+        case 'I':
+        case 'j':
+        case 'J':
+        case 'k':
+        case 'K':
+        case 'l':
+        case 'L':
+        case 'm':
+        case 'M':
+        case 'n':
+        case 'N':
+        case 'o':
+        case 'O':
+        case 'p':
+        case 'P':
+        case 'q':
+        case 'Q':
+        case 'r':
+        case 'R':
+        case 's':
+        case 'S':
+        case 't':
+        case 'T':
+        case 'u':
+        case 'U':
+        case 'v':
+        case 'V':
+        case 'w':
+        case 'W':
+        case 'x':
+        case 'X':
+        case 'y':
+        case 'Y':
+        case 'z':
+        case 'Z':
+        case '0':
+        case '1':
+        case '2':
+        case '3':
+        case '4':
+        case '5':
+        case '6':
+        case '7':
+        case '8':
+        case '9':
+        case '-':
+        case '_':
+        case '.':
+        case '~':
+          /**
+           * Unreserved characters can (and should!) stay unchanged!
+           * (See {@link http://en.wikipedia.org/wiki/Percent-encoding#Types_of_URI_characters})
+           */
+          out.append(Character.toChars(codePoint));
+          break;
+        default:
+          /**
+           * All other characters are reserved or special characters and,
+           * hence, must be encoded!
+           */
+          String encoded = new String(Character.toChars(codePoint));
+          byte[] bytes = encoded.getBytes(charset);
+          for (int j = 0; j < bytes.length; j++) {
+            out.append('%');
+            out.append(Character.forDigit((bytes[j] >> 4) & 0xF, 16));
+            out.append(Character.forDigit((bytes[j]) & 0xF, 16));
+          }
+      }
+    }
+    return out.toString();
+  }
+
+  public String decode(CharSequence in) {
+    StringBuilder out = new StringBuilder();
+    int i = 0;
+    int length = in.length();
+    while (i < length) {
+      char c = in.charAt(i);
+      if (c != '%') {
+        out.append(c);
+        i++;
+      }
+      else {
+        byte[] bytes = new byte[length-i/3];
+        int pos = 0;
+        while (i+2 < length && in.charAt(i) == '%' ) {
+          int b = 0;
+          switch (in.charAt(i+1)) {
+            case '0': break;
+            case '1': b = 16*1; break;
+            case '2': b = 16*2; break;
+            case '3': b = 16*3; break;
+            case '4': b = 16*4; break;
+            case '5': b = 16*5; break;
+            case '6': b = 16*6; break;
+            case '7': b = 16*7; break;
+            case '8': b = 16*8; break;
+            case '9': b = 16*9; break;
+            case 'a':
+            case 'A': b = 16*10; break;
+            case 'b':
+            case 'B': b = 16*11; break;
+            case 'c':
+            case 'C': b = 16*12; break;
+            case 'd':
+            case 'D': b = 16*13; break;
+            case 'e':
+            case 'E': b = 16*14; break;
+            case 'f':
+            case 'F': b = 16*15; break;
+            default: throw new IllegalArgumentException("Illegal escape-sequence: %" + in.subSequence(i, i+3));
+          }
+          switch (in.charAt(i+2)) {
+            case '0': break;
+            case '1': b += 1; break;
+            case '2': b += 2; break;
+            case '3': b += 3; break;
+            case '4': b += 4; break;
+            case '5': b += 5; break;
+            case '6': b += 6; break;
+            case '7': b += 7; break;
+            case '8': b += 8; break;
+            case '9': b += 9; break;
+            case 'a':
+            case 'A': b += 10; break;
+            case 'b':
+            case 'B': b += 11; break;
+            case 'c':
+            case 'C': b += 12; break;
+            case 'd':
+            case 'D': b += 13; break;
+            case 'e':
+            case 'E': b += 14; break;
+            case 'f':
+            case 'F': b += 15; break;
+            default: throw new IllegalArgumentException("Illegal escape-sequence: %" + in.subSequence(i, i+3));
+          }
+          bytes[pos++] = (byte)b;
+          i += 3;
+        }
+        out.append(new String(bytes, 0, pos, charset));
+        if (i < length && in.charAt(i) == '%')
+          throw  new IllegalArgumentException("Incomplete escape-sequence: %" + in.subSequence(i, length));
+      }
+    }
+    return out.toString();
+  }
+}