diff --git a/htroot/PerformanceMemory_p.java b/htroot/PerformanceMemory_p.java index ccbbc6208..07e689a21 100644 --- a/htroot/PerformanceMemory_p.java +++ b/htroot/PerformanceMemory_p.java @@ -340,7 +340,6 @@ public class PerformanceMemory_p { usd = chk * slt[1] + obj * ost[2] /*hit*/ + kelondroTree.cacheObjectMissSize * ost[3] /*miss*/; bst = (((((long) chk) * ((long) req)) >> 10) + 1) << 10; if (set.equals("setBest")) env.setConfig("ramCache" + db, bst); - System.out.println(wdb + ((wdb.length() > 0) ? ("_") : ("")) + "nodsc" + db); prop.put(wdb + ((wdb.length() > 0) ? ("_") : ("")) + "nodsz" + db, chk); prop.put(wdb + ((wdb.length() > 0) ? ("_") : ("")) + "ochunksiz" + db, obj); prop.put(wdb + ((wdb.length() > 0) ? ("_") : ("")) + "slreq" + db, req); diff --git a/source/de/anomic/net/URL.java b/source/de/anomic/net/URL.java index ea4d170c7..c6a9f9874 100644 --- a/source/de/anomic/net/URL.java +++ b/source/de/anomic/net/URL.java @@ -76,6 +76,7 @@ public class URL { identPort(url); identRef(); identQuest(); + if (path.indexOf('%')==-1) escapePath(); } else { // this is not a http or ftp url if (protocol.equals("mailto")) { @@ -95,7 +96,6 @@ public class URL { throw new MalformedURLException("unknown protocol: " + url); } } - } public URL(File file) throws MalformedURLException { @@ -145,6 +145,7 @@ public class URL { resolveBackpath(); identRef(); identQuest(); + if (path.indexOf('%')==-1) escapePath(); } } @@ -156,6 +157,7 @@ public class URL { this.path = path; identRef(); identQuest(); + if (path.indexOf('%')==-1) escapePath(); } private void resolveBackpath() throws MalformedURLException { @@ -169,6 +171,163 @@ public class URL { } } + private void escapePath() { + String[] pathp = path.split("/",-1); + String ptmp = ""; + for (int i = 0; i0) ? 1 : 0); + } + + final static String[] hex = { + "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07", + "%08", "%09", "%0a", "%0b", "%0c", "%0d", "%0e", "%0f", + "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17", + "%18", "%19", "%1a", "%1b", "%1c", "%1d", "%1e", "%1f", + "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27", + "%28", "%29", "%2a", "%2b", "%2c", "%2d", "%2e", "%2f", + "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37", + "%38", "%39", "%3a", "%3b", "%3c", "%3d", "%3e", "%3f", + "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47", + "%48", "%49", "%4a", "%4b", "%4c", "%4d", "%4e", "%4f", + "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57", + "%58", "%59", "%5a", "%5b", "%5c", "%5d", "%5e", "%5f", + "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67", + "%68", "%69", "%6a", "%6b", "%6c", "%6d", "%6e", "%6f", + "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77", + "%78", "%79", "%7a", "%7b", "%7c", "%7d", "%7e", "%7f", + "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87", + "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f", + "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97", + "%98", "%99", "%9a", "%9b", "%9c", "%9d", "%9e", "%9f", + "%a0", "%a1", "%a2", "%a3", "%a4", "%a5", "%a6", "%a7", + "%a8", "%a9", "%aa", "%ab", "%ac", "%ad", "%ae", "%af", + "%b0", "%b1", "%b2", "%b3", "%b4", "%b5", "%b6", "%b7", + "%b8", "%b9", "%ba", "%bb", "%bc", "%bd", "%be", "%bf", + "%c0", "%c1", "%c2", "%c3", "%c4", "%c5", "%c6", "%c7", + "%c8", "%c9", "%ca", "%cb", "%cc", "%cd", "%ce", "%cf", + "%d0", "%d1", "%d2", "%d3", "%d4", "%d5", "%d6", "%d7", + "%d8", "%d9", "%da", "%db", "%dc", "%dd", "%de", "%df", + "%e0", "%e1", "%e2", "%e3", "%e4", "%e5", "%e6", "%e7", + "%e8", "%e9", "%ea", "%eb", "%ec", "%ed", "%ee", "%ef", + "%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7", + "%f8", "%f9", "%fa", "%fb", "%fc", "%fd", "%fe", "%ff" + }; + + /** + * Encode a string to the "x-www-form-urlencoded" form, enhanced + * with the UTF-8-in-URL proposal. This is what happens: + * + * + * + * @param s The string to be encoded + * @return The encoded string + */ + // from: http://www.w3.org/International/URLUTF8Encoder.java + public static String escape(String s) + { + StringBuffer sbuf = new StringBuffer(); + int len = s.length(); + for (int i = 0; i < len; i++) { + int ch = s.charAt(i); + if ('A' <= ch && ch <= 'Z') { // 'A'..'Z' + sbuf.append((char)ch); + } else if ('a' <= ch && ch <= 'z') { // 'a'..'z' + sbuf.append((char)ch); + } else if ('0' <= ch && ch <= '9') { // '0'..'9' + sbuf.append((char)ch); + } else if (ch == ' ') { // space + sbuf.append("%20"); + } else if (ch == '-' || ch == '_' // unreserved + || ch == '.' || ch == '!' + || ch == '~' || ch == '*' + || ch == '\'' || ch == '(' + || ch == ')' || ch == '%') { + sbuf.append((char)ch); + } else if (ch <= 0x007f) { // other ASCII + sbuf.append(hex[ch]); + } else if (ch <= 0x07FF) { // non-ASCII <= 0x7FF + sbuf.append(hex[0xc0 | (ch >> 6)]); + sbuf.append(hex[0x80 | (ch & 0x3F)]); + } else { // 0x7FF < ch <= 0xFFFF + sbuf.append(hex[0xe0 | (ch >> 12)]); + sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]); + sbuf.append(hex[0x80 | (ch & 0x3F)]); + } + } + return sbuf.toString(); + } + + // from: http://www.w3.org/International/unescape.java + public static String unescape(String s) { + StringBuffer sbuf = new StringBuffer () ; + int l = s.length(); + int ch = -1; + int b, sumb = 0; + for (int i = 0, more = -1 ; i < l ; i++) { + /* Get next byte b from URL segment s */ + switch (ch = s.charAt(i)) { + case '%': + ch = s.charAt (++i) ; + int hb = (Character.isDigit ((char) ch) + ? ch - '0' + : 10+Character.toLowerCase((char) ch) - 'a') & 0xF ; + ch = s.charAt (++i) ; + int lb = (Character.isDigit ((char) ch) + ? ch - '0' + : 10+Character.toLowerCase ((char) ch)-'a') & 0xF ; + b = (hb << 4) | lb ; + break ; + case '+': + b = ' ' ; + break ; + default: + b = ch ; + } + /* Decode byte b as UTF-8, sumb collects incomplete chars */ + if ((b & 0xc0) == 0x80) { // 10xxxxxx (continuation byte) + sumb = (sumb << 6) | (b & 0x3f) ; // Add 6 bits to sumb + if (--more == 0) sbuf.append((char) sumb) ; // Add char to sbuf + } else if ((b & 0x80) == 0x00) { // 0xxxxxxx (yields 7 bits) + sbuf.append((char) b) ; // Store in sbuf + } else if ((b & 0xe0) == 0xc0) { // 110xxxxx (yields 5 bits) + sumb = b & 0x1f; + more = 1; // Expect 1 more byte + } else if ((b & 0xf0) == 0xe0) { // 1110xxxx (yields 4 bits) + sumb = b & 0x0f; + more = 2; // Expect 2 more bytes + } else if ((b & 0xf8) == 0xf0) { // 11110xxx (yields 3 bits) + sumb = b & 0x07; + more = 3; // Expect 3 more bytes + } else if ((b & 0xfc) == 0xf8) { // 111110xx (yields 2 bits) + sumb = b & 0x03; + more = 4; // Expect 4 more bytes + } else /*if ((b & 0xfe) == 0xfc)*/ { // 1111110x (yields 1 bit) + sumb = b & 0x01; + more = 5; // Expect 5 more bytes + } + /* We don't test if the UTF-8 encoding is well-formed */ + } + return sbuf.toString() ; + } + private void identPort(String inputURL) throws MalformedURLException { // identify ref in file int r = host.indexOf(':'); @@ -323,7 +482,11 @@ public class URL { new String[]{"http://www.anomic.de/home", "news:de.test"}, new String[]{"http://www.anomic.de/home", "ftp://ftp.anomic.de/src"}, new String[]{null, "ftp://ftp.delegate.org/"}, - new String[]{"http://www.anomic.de/home", "ftp://ftp.delegate.org/"} + new String[]{"http://www.anomic.de/home", "ftp://ftp.delegate.org/"}, + new String[]{null,"http://www.bla.org/bli bla blo"}, + new String[]{null,"http://www.blubb.org/bli bla/ blo blubb/bla.html"}, + new String[]{null,"http://california-press-release.com/30/Hendrick Chevrolet, the renowned car dealer for Chevrolet in Cary, North Carolina (NC) announces the arrival of 2007 Chevrolet Cobalt SS Coupe For further information, call Hendrick Chevrolet on (800)-857-4909.php"}, + new String[]{"http://california-press-release.com","30/Hendrick Chevrolet, the renowned car dealer for Chevrolet in Cary, North Carolina (NC) announces the arrival of 2007 Chevrolet Cobalt SS Coupe For further information, call Hendrick Chevrolet on (800)-857-4909.php"} }; String environment, url; de.anomic.net.URL aURL = null; @@ -337,15 +500,15 @@ public class URL { } else { try {aURL = new de.anomic.net.URL(new de.anomic.net.URL(environment), url);} catch (MalformedURLException e) {aURL = null;} try {jURL = new java.net.URL(new java.net.URL(environment), url);} catch (MalformedURLException e) {jURL = null;} - } + }/* if (((aURL == null) && (jURL != null)) || ((aURL != null) && (jURL == null)) || - ((aURL != null) && (jURL != null) && (!(jURL.toString().equals(aURL.toString()))))) { + ((aURL != null) && (jURL != null) && (!(jURL.toString().equals(aURL.toString()))))) {*/ System.out.println("Difference for environment=" + environment + ", url=" + url + ":"); System.out.println((jURL == null) ? "jURL rejected input" : "jURL=" + jURL.toString()); System.out.println((aURL == null) ? "aURL rejected input" : "aURL=" + aURL.toString()); System.out.println(); - } + //} } } }