version bump 1.3.8: node inconsistency workaround

- Changing Buffer length is inconsistent, remedy is to explicitly slice buffer
- updated test artifacts
- added some notes to README

Author: SheetJSDev

README.md

@@ -1,8 +1,8 @@
 # Codepages for JS
 
 [Codepages](https://en.wikipedia.org/wiki/Codepage) are character encodings.  In
-many contexts, single-byte character sets are used in lieu of standard multibyte
-Unicode encodings.  They use 256 characters with a simple mapping.
+many contexts, single- or double-byte character sets are used in lieu of Unicode
+encodings.  The codepages map between characters and numbers.
 
 [unicode.org](http://www.unicode.org/Public/MAPPINGS/) hosts lists of mappings.
 The build script automatically downloads and parses the mappings in order to
@@ -81,7 +81,35 @@ In node:
 
     var cptable = require('codepage/dist/cpexcel.full');
 
-## Building the script
+## Rolling your own script
+
+The `make.sh` script in the repo can take a manifest and generate JS source.
+
+Usage:
+
+    bash make.sh path_to_manifest output_file_name JSVAR
+
+where
+
+- `JSVAR` is the name of the exported variable (generally `cptable`)
+- `output_file_name` is the output file (e.g. `cpexcel.js`, `cptable.js`)
+- `path_to_manifest` is the path to the manifest file.
+
+The manifest file is expected to be a CSV with 3 columns:
+
+    <codepage number>,<source>,<size>
+
+If a source is specified, it will try to download the specified file and parse.
+The file format is expected to follow the format from the unicode.org site.
+The size should be `1` for a single-byte codepage and `2` for a double-byte
+codepage.  For mixed codepages (which use some single- and some double-byte
+codes), the script assumes the mapping is a prefix code and generates efficient
+JS code.
+
+Generated scripts only include the mapping.  `cat` a mapping with `cputils.js`
+to produce a complete script like `cpexcel.full.js`.
+
+## Building the complete script
 
 This script uses [voc](npm.im/voc).  The script to build the codepage tables and
 the JS source is `codepage.md`, so building is as simple as `voc codepage.md`.
@@ -94,10 +122,11 @@ Some codepages are easier to implement algorithmically.  Since these are
 hardcoded in utils, there is no corresponding entry (they are "magic")
 
 | CP# |  Information  | Description |
-| --: |  -----------  | ----------- |
+| --: |  :----------: | :---------- |
 |   37|  unicode.org  |IBM EBCDIC US-Canada
 |  437|  unicode.org  |OEM United States
 |  500|  unicode.org  |IBM EBCDIC International
+|  620|      NLS      |Mazovia (Polish) MS-DOS
 |  708|MakeEncoding.cs|Arabic (ASMO 708)
 |  720|MakeEncoding.cs|Arabic (Transparent ASMO); Arabic (DOS)
 |  737|  unicode.org  |OEM Greek (formerly 437G); Greek (DOS)
@@ -118,6 +147,7 @@ hardcoded in utils, there is no corresponding entry (they are "magic")
 |  870|MakeEncoding.cs|IBM EBCDIC Multilingual/ROECE (Latin 2)
 |  874|  unicode.org  |Windows Thai
 |  875|  unicode.org  |IBM EBCDIC Greek Modern
+|  895|      NLS      |Kamenický (Czech) MS-DOS
 |  932|  unicode.org  |Japanese Shift-JIS
 |  936|  unicode.org  |Simplified Chinese GBK
 |  949|  unicode.org  |Korean

codepage.md

@@ -729,7 +729,7 @@ describe('failures', function() {
 ```json>package.json
 {
   "name": "codepage",
-  "version": "1.3.7",
+  "version": "1.3.8",
   "author": "SheetJS",
   "description": "pure-JS library to handle codepages",
   "keywords": [ "codepage", "iconv", "convert", "strings" ],

cpexcel.js

@@ -32,7 +32,9 @@
 
   var sfcc = function sfcc(x) { return String.fromCharCode(x); };
   var cca = function cca(x){ return x.charCodeAt(0); };
-  if(typeof Buffer !== 'undefined') {
+
+  var has_buf = (typeof Buffer !== 'undefined');
+  if(has_buf) {
     var mdl = 1024, mdb = new Buffer(mdl);
     var make_EE = function make_EE(E){
       var EE = new Buffer(65536);
@@ -67,6 +69,7 @@
             }
           }
           out.length = j;
+          out = out.slice(0,j);
         } else {
           out = Buffer(len);
           for(i = 0; i < len; ++i) out[i] = EE[data[i].charCodeAt(0)];
@@ -125,6 +128,7 @@
             out[k++] = EE[j+1] || EE[j]; if(EE[j+1] > 0) out[k++] = EE[j];
           }
           out.length = k;
+          out = out.slice(0,k);
         } else if(Buffer.isBuffer(data)) {
           for(i = k = 0; i < len; ++i) {
             D = data[i];
@@ -139,6 +143,7 @@
             }
           }
           out.length = k;
+          out = out.slice(0,k);
         } else {
           for(i = k = 0; i < len; i++) {
             j = data[i].charCodeAt(0)*2;
@@ -237,7 +242,7 @@
   }
 
   var encache = function encache() {
-    if(typeof Buffer !== 'undefined') {
+    if(has_buf) {
       if(cpdcache[sbcs_cache[0]]) return;
       var i, s;
       for(i = 0; i < sbcs_cache.length; ++i) {
@@ -263,7 +268,7 @@
   };
   var cp_decache = function cp_decache(cp) { cpdcache[cp] = cpecache[cp] = undefined; };
   var decache = function decache() {
-    if(typeof Buffer !== 'undefined') {
+    if(has_buf) {
       if(!cpdcache[sbcs_cache[0]]) return;
       sbcs_cache.forEach(cp_decache);
       dbcs_cache.forEach(cp_decache);
@@ -286,9 +291,9 @@
   var encode = function encode(cp, data, ofmt) {
     if(cp === last_cp) { return last_enc(data, ofmt); }
     if(cpecache[cp] !== undefined) { last_enc = cpecache[last_cp=cp]; return last_enc(data, ofmt); }
-    if(typeof Buffer !== 'undefined' && Buffer.isBuffer(data)) data = data.toString('utf8');
+    if(has_buf && Buffer.isBuffer(data)) data = data.toString('utf8');
     var len = data.length;
-    var out = typeof Buffer !== 'undefined' ? new Buffer(4*len) : [], w, i, j = 0, c, tt, ww;
+    var out = has_buf ? new Buffer(4*len) : [], w, i, j = 0, c, tt, ww;
     var C = cpt[cp], E, M;
     if(C && (E=C.enc)) for(i = 0; i < len; ++i, ++j) {
       w = E[data[i]];
@@ -300,7 +305,7 @@
     }
     else if((M=magic[cp])) switch(M) {
       case "utf8":
-        if(typeof Buffer !== 'undefined' && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
+        if(has_buf && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
         for(i = 0; i < len; ++i, ++j) {
           w = data[i].charCodeAt(0);
           if(w <= 0x007F) out[j] = w;
@@ -322,15 +327,15 @@
         }
         break;
       case "ascii":
-        if(typeof Buffer !== 'undefined' && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
+        if(has_buf && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
         for(i = 0; i < len; ++i, ++j) {
           w = data[i].charCodeAt(0);
           if(w <= 0x007F) out[j] = w;
           else throw new Error("bad ascii " + w);
         }
         break;
       case "utf16le":
-        if(typeof Buffer !== 'undefined' && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
+        if(has_buf && typeof data === "string") { out = new Buffer(data, M); j = out.length; break; }
         for(i = 0; i < len; ++i) {
           w = data[i].charCodeAt(0);
           out[j++] = w&255;
@@ -382,6 +387,7 @@
     }
     else throw new Error("Unrecognized CP: " + cp);
     out.length = j;
+    out = out.slice(0,j);
     if(typeof Buffer === 'undefined') return (ofmt == 'str') ? out.map(sfcc).join("") : out;
     if(ofmt === undefined || ofmt === 'buf') return out;
     if(ofmt !== 'arr') return out.toString('binary');
@@ -422,13 +428,13 @@
         }
         break;
       case "ascii":
-        if(typeof Buffer !== 'undefined' && Buffer.isBuffer(data)) return data.toString(M);
+        if(has_buf && Buffer.isBuffer(data)) return data.toString(M);
         for(i = 0; i < len; i++) out[i] = String.fromCharCode(data[i]);
         k = len; break;
       case "utf16le":
         i = 0;
         if(len >= 2 && data[0] == 0xFF) if(data[1] == 0xFE) i = 2;
-        if(typeof Buffer !== 'undefined' && Buffer.isBuffer(data)) return data.toString(M);
+        if(has_buf && Buffer.isBuffer(data)) return data.toString(M);
         j = 2;
         for(; i < len; i+=j) {
           out[k++] = String.fromCharCode((data[i+1]<<8) + data[i]);