yauzl - npm Package Compare versions

Comparing version 0.0.0 to 1.0.0

index.js

 var fs = require("fs");
 var zlib = require("zlib");
 var FdSlicer = require("fd-slicer");
+var util = require("util");
+var EventEmitter = require("events").EventEmitter;
+var Iconv = require("iconv").Iconv;
 
@@ -14,7 +17,12 @@ exports.open = open;
 
-function open(path, callback) {
+function open(path, options, callback) {
+  if (typeof options === "function") {
+    callback = options;
+    options = null;
+  }
+  if (options == null) options = {autoClose: true};
   if (callback == null) callback = defaultCallback;
   fs.open(path, "r", function(err, fd) {
     if (err) return callback(err);
-    fopen(fd, function(err, zipfile) {
+    fopen(fd, options, function(err, zipfile) {
       if (err) fs.close(fd, defaultCallback);
@@ -26,3 +34,8 @@ callback(err, zipfile);
 
-function fopen(fd, callback) {
+function fopen(fd, options, callback) {
+  if (typeof options === "function") {
+    callback = options;
+    options = null;
+  }
+  if (options == null) options = {autoClose: false};
   if (callback == null) callback = defaultCallback;
@@ -66,7 +79,5 @@ fs.fstat(fd, function(err, stats) {
         // 22 - Comment
-        var comment = new Buffer(commentLength);
-        // the comment length is typcially 0.
-        // copy from the original buffer to make sure we're not pinning it from being GC'ed.
-        eocdrBuffer.copy(comment, 0, 22, eocdrBuffer.length);
-        return callback(null, new ZipFile(fd, cdOffset, entryCount, comment));
+        // the encoding is always cp437.
+        var comment = bufferToString(eocdrBuffer, 22, eocdrBuffer.length, false);
+        return callback(null, new ZipFile(fd, cdOffset, entryCount, comment, options.autoClose));
       }
@@ -78,44 +89,49 @@ callback(new Error("end of central directory record signature not found"));
 
-function ZipFile(fd, cdOffset, entryCount, comment) {
-  this.fdSlicer = new FdSlicer(fd);
-  this.readEntryCursor = cdOffset;
-  this.entryCount = entryCount;
-  this.comment = comment;
-  this.entriesRead = 0;
-  this.isReadingEntry = false;
+util.inherits(ZipFile, EventEmitter);
+function ZipFile(fd, cdOffset, entryCount, comment, autoClose) {
+  var self = this;
+  EventEmitter.call(self);
+  self.fdSlicer = new FdSlicer(fd, {autoClose: true});
+  self.fdSlicer.ref();
+  // forward close events
+  self.fdSlicer.on("error", function(err) {
+    // error closing the fd
+    self.emit("error", err);
+  });
+  self.fdSlicer.once("close", function() {
+    self.emit("close");
+  });
+  self.readEntryCursor = cdOffset;
+  self.entryCount = entryCount;
+  self.comment = comment;
+  self.entriesRead = 0;
+  self.autoClose = !!autoClose;
+  self.isOpen = true;
+  // make sure events don't fire outta here until the client has a chance to attach listeners
+  setImmediate(function() { readEntries(self); });
 }
-ZipFile.prototype.close = function(callback) {
-  if (callback == null) callback = defaultCallback;
-  fs.close(this.fdSlicer.fd, callback);
+ZipFile.prototype.close = function() {
+  if (!this.isOpen) return;
+  this.isOpen = false;
+  this.fdSlicer.unref();
 };
-ZipFile.prototype.readEntries = function(callback) {
-  var self = this;
-  if (callback == null) callback = defaultCallback;
-  self.entries = [];
-  // setImmediate here to make sure callback is called asynchronously even if there are 0 entries left.
-  setImmediate(keepReading);
-  function keepReading() {
-    if (self.entriesRemaining() === 0) return callback(null, self.entries);
-    self.readEntry(function(err, entry) {
-      if (err) return callback(err);
-      self.entries.push(entry);
-      keepReading();
-    });
+
+function emitErrorAndAutoClose(self, err) {
+  if (self.autoClose) self.close();
+  self.emit("error", err);
+}
+
+function readEntries(self) {
+  if (self.entryCount === self.entriesRead) {
+    // done with metadata
+    if (self.autoClose) self.close();
+    return self.emit("end");
   }
-};
-ZipFile.prototype.entriesRemaining = function() {
-  return this.entryCount - this.entriesRead;
-};
-ZipFile.prototype.readEntry = function(callback) {
-  var self = this;
-  if (self.isReadingEntry) throw new Error("readEntry already in progress");
-  self.isReadingEntry = true;
-  if (callback == null) callback = defaultCallback;
   var buffer = new Buffer(46);
-  readFdSlicerNoEof(this.fdSlicer, buffer, 0, buffer.length, this.readEntryCursor, function(err) {
-    if (err) return callback(err);
+  readFdSlicerNoEof(self.fdSlicer, buffer, 0, buffer.length, self.readEntryCursor, function(err) {
+    if (err) return emitErrorAndAutoClose(self, err);
     var entry = new Entry();
     // 0 - Central directory file header signature
     var signature = buffer.readUInt32LE(0);
-    if (signature !== 0x02014b50) return callback(new Error("invalid central directory file header signature: 0x" + signature.toString(16)));
+    if (signature !== 0x02014b50) return emitErrorAndAutoClose(self, new Error("invalid central directory file header signature: 0x" + signature.toString(16)));
     // 4 - Version made by
@@ -157,7 +173,6 @@ entry.versionMadeBy = buffer.readUInt16LE(4);
     readFdSlicerNoEof(self.fdSlicer, buffer, 0, buffer.length, self.readEntryCursor, function(err) {
-      if (err) return callback(err);
+      if (err) return emitErrorAndAutoClose(self, err);
       // 46 - File name
-      var encoding = entry.generalPurposeBitFlag & 0x800 ? "utf8" : "ascii";
-      // TODO: replace ascii with CP437 using https://github.com/bnoordhuis/node-iconv
-      entry.fileName = buffer.toString(encoding, 0, entry.fileNameLength);
+      var isUtf8 = entry.generalPurposeBitFlag & 0x800
+      entry.fileName = bufferToString(buffer, 0, entry.fileNameLength);
 
@@ -184,53 +199,63 @@ // 46+n - Extra field
       // 46+n+m - File comment
-      entry.fileComment = buffer.toString(encoding, fileCommentStart, fileCommentStart + entry.fileCommentLength);
+      entry.fileComment = bufferToString(buffer, fileCommentStart, fileCommentStart + entry.fileCommentLength);
 
       self.readEntryCursor += buffer.length;
       self.entriesRead += 1;
-      self.isReadingEntry = false;
 
-      callback(null, entry);
+      // validate file name
+      if (entry.fileName.indexOf("\\") !== -1) return emitErrorAndAutoClose(self, new Error("invalid characters in fileName: " + entry.fileName));
+      if (/^[a-zA-Z]:/.exec(entry.fileName) || /^\//.exec(entry.fileName)) return emitErrorAndAutoClose(self, new Error("absolute path: " + entry.fileName));
+      self.emit("entry", entry);
+      readEntries(self);
     });
   });
-};
+}
 
 ZipFile.prototype.openReadStream = function(entry, callback) {
   var self = this;
+  if (!self.isOpen) return self.emit("error", new Error("closed"));
+  // make sure we don't lose the fd before we open the actual read stream
+  self.fdSlicer.ref();
   var buffer = new Buffer(30);
   readFdSlicerNoEof(self.fdSlicer, buffer, 0, buffer.length, entry.relativeOffsetOfLocalHeader, function(err) {
-    if (err) return callback(err);
-    // 0 - Local file header signature = 0x04034b50
-    var signature = buffer.readUInt32LE(0);
-    if (signature !== 0x04034b50) return callback(new Error("invalid local file header signature: 0x" + signature.toString(16)));
-    // all this should be redundant
-    // 4 - Version needed to extract (minimum)
-    // 6 - General purpose bit flag
-    // 8 - Compression method
-    // 10 - File last modification time
-    // 12 - File last modification date
-    // 14 - CRC-32
-    // 18 - Compressed size
-    // 22 - Uncompressed size
-    // 26 - File name length (n)
-    var fileNameLength = buffer.readUInt16LE(26);
-    // 28 - Extra field length (m)
-    var extraFieldLength = buffer.readUInt16LE(28);
-    // 30 - File name
-    // 30+n - Extra field
-    var localFileHeaderEnd = entry.relativeOffsetOfLocalHeader + buffer.length + fileNameLength + extraFieldLength;
-    var filterStream = null;
-    if (entry.compressionMethod === 0) {
-      // 0 - The file is stored (no compression)
-    } else if (entry.compressionMethod === 8) {
-      // 8 - The file is Deflated
-      filterStream = zlib.createInflateRaw();
-    } else {
-      return callback(new Error("unsupported compression method: " + entry.compressionMethod));
+    try {
+      if (err) return callback(err);
+      // 0 - Local file header signature = 0x04034b50
+      var signature = buffer.readUInt32LE(0);
+      if (signature !== 0x04034b50) return callback(new Error("invalid local file header signature: 0x" + signature.toString(16)));
+      // all this should be redundant
+      // 4 - Version needed to extract (minimum)
+      // 6 - General purpose bit flag
+      // 8 - Compression method
+      // 10 - File last modification time
+      // 12 - File last modification date
+      // 14 - CRC-32
+      // 18 - Compressed size
+      // 22 - Uncompressed size
+      // 26 - File name length (n)
+      var fileNameLength = buffer.readUInt16LE(26);
+      // 28 - Extra field length (m)
+      var extraFieldLength = buffer.readUInt16LE(28);
+      // 30 - File name
+      // 30+n - Extra field
+      var localFileHeaderEnd = entry.relativeOffsetOfLocalHeader + buffer.length + fileNameLength + extraFieldLength;
+      var filterStream = null;
+      if (entry.compressionMethod === 0) {
+        // 0 - The file is stored (no compression)
+      } else if (entry.compressionMethod === 8) {
+        // 8 - The file is Deflated
+        filterStream = zlib.createInflateRaw();
+      } else {
+        return callback(new Error("unsupported compression method: " + entry.compressionMethod));
+      }
+      var fileDataStart = localFileHeaderEnd;
+      var fileDataEnd = fileDataStart + entry.compressedSize;
+      var stream = self.fdSlicer.createReadStream({start: fileDataStart, end: fileDataEnd});
+      if (filterStream != null) {
+        stream = stream.pipe(filterStream);
+      }
+      callback(null, stream);
+    } finally {
+      self.fdSlicer.unref();
     }
-    var fileDataStart = localFileHeaderEnd;
-    var fileDataEnd = fileDataStart + entry.compressedSize;
-    var stream = self.fdSlicer.createReadStream({start: fileDataStart, end: fileDataEnd});
-    if (filterStream != null) {
-      stream = stream.pipe(filterStream);
-    }
-    callback(null, stream);
   });
@@ -256,4 +281,12 @@ };
 }
+var cp437_to_utf8 = new Iconv("cp437", "utf8");
+function bufferToString(buffer, start, end, isUtf8) {
+  if (isUtf8) {
+    return buffer.toString("utf8", start, end);
+  } else {
+    return cp437_to_utf8.convert(buffer.slice(start, end)).toString("utf8");
+  }
+}
 function defaultCallback(err) {
   if (err) throw err;
 }

package.json

 {
   "name": "yauzl",
-  "version": "0.0.0",
+  "version": "1.0.0",
   "description": "yet another unzip library for node",
   "main": "index.js",
+  "scripts": {
+    "test": "node test/test.js"
+  },
   "repository": {
@@ -20,4 +23,6 @@ "type": "git",
   "dependencies": {
-    "fd-slicer": "~0.2.1"
+    "fd-slicer": "~0.2.1",
+    "iconv": "~2.1.4",
+    "pend": "~1.1.3"
   }
 }

README.md

@@ -11,3 +11,3 @@ # yauzl
  * Don't block the JavaScript thread.
-   Use and provide async apis.
+   Use and provide async APIs.
  * Keep memory usage under control.
@@ -20,13 +20,15 @@ Don't attempt to buffer entire files in RAM at once.
 var yauzl = require("yauzl");
-var fs = require('fs');
+var fs = require("fs");
 
 yauzl.open("path/to/file.zip", function(err, zipfile) {
   if (err) throw err;
-  zipfile.readEntries(function(err, entries) {
-    if (err) throw err;
-    entries.forEach(function(entry) {
-      zipfile.openReadStream(entry, function(err, readStream) {
-        if (err) throw err;
-        readStream.pipe(fs.createWriteStream(entry.fileName));
-      });
+  zipfile.on("entry", function(entry) {
+    if (/\/$/.exec(entry.fileName)) {
+      // directory file names end with '/'
+      return;
+    }
+    zipfile.openReadStream(entry, function(err, readStream) {
+      if (err) throw err;
+      // ensure parent directory exists, and then:
+      readStream.pipe(fs.createWriteStream(entry.fileName));
     });
@@ -47,8 +49,10 @@ });
 
-### open(path, [callback])
+### open(path, [options], [callback])
 
-Calls `fs.open(path, "r")` and gives the `fd` and `callback` to `fopen` below.
+Calls `fs.open(path, "r")` and gives the `fd`, `options`, and `callback` to `fopen` below.
 
-### fopen(fd, [callback])
+`options` may be omitted or `null` and defaults to `{autoClose: true}`.
 
+### fopen(fd, [options], [callback])
+
 Reads from the fd, which is presumed to be an open .zip file.
@@ -63,15 +67,30 @@ Note that random access is required by the zip file specification,
 
-### class ZipFile
+`options` may be omitted or `null` and defaults to `{autoClose: false}`.
+`autoClose` is effectively equivalent to:
 
+```js
+zipfile.once("end", function() {
+  zipfile.close();
+});
+```
+
+### Class: ZipFile
+
 The constructor for the class is not part of the public API.
 Use `open` or `fopen` instead.
 
-#### close([callback])
+#### Event: "entry"
 
-Calls `fs.close(fd, callback)`.
+Callback gets `(entry)`, which is an `Entry`.
 
-#### readEntries([callback])
+#### Event: "end"
 
-`callback` gets `(err, entries)`, where `entries` is an `Array` of `Entry` objects.
+Emitted after the last `entry` event has been emitted.
 
+#### Event: "close"
+
+Emitted after the fd is actually closed.
+This is after calling `close` (or after the `end` event when `autoClose` is `true`),
+and after all streams created from `openReadStream` have emitted their `end` events.
+
 #### openReadStream(entry, [callback])
@@ -83,18 +102,17 @@
 the read stream provides the decompressed data.
+If this zipfile is already closed (see `close`), the `callback` will receive an `err`.
 
-#### entriesRemaining()
+#### close([callback])
 
-Returns the number of entries in this `ZipFile` that have not yet been returned by `readEntry`.
+Causes all future calls to `openReadStream` to fail,
+and calls `fs.close(fd, callback)` after all streams created by `openReadStream` have emitted their `end` events.
+If this object's `end` event has not been emitted yet, this function causes undefined behavior.
 
-#### readEntry([callback])
+If `autoClose` is `true` in the original `open` or `fopen` call,
+this function will be called automatically effectively in response to this object's `end` event.
 
-Most clients should use the `readEntries` function.
-`readEntry` and `entriesRemaining` provide low-level access for reading one entry at a time.
-This can be useful if the index were very large, and you wanted to start reading entries right away.
+#### isOpen
 
-Calling this function directly sabotages the `readEntries` function.
-You must not call this function before any previous call to this function completes by calling its `callback`.
+`Boolean`. `true` until `close` is called; then it's `false`.
 
-TODO: really? This API is super sketchy.
-
 #### entryCount
@@ -106,5 +124,5 @@
 
-`Buffer`. TODO: decode with `cp473`.
+`String`. Always decoded with `CP437` per the spec.
 
-### class Entry
+### Class: Entry
 
@@ -114,3 +132,3 @@ Objects of this class represent Central Directory Records.
 
-These fields are numbers:
+These fields are of type `Number`:
 
@@ -126,5 +144,5 @@ * `versionMadeBy`
  * `uncompressedSize`
- * `fileNameLength`
- * `extraFieldLength`
- * `fileCommentLength`
+ * `fileNameLength` (bytes)
+ * `extraFieldLength` (bytes)
+ * `fileCommentLength` (bytes)
  * `internalFileAttributes`
@@ -137,9 +155,9 @@ * `externalFileAttributes`
 `String`.
-The bytes in the file are decoded with `utf8` if `generalPurposeBitFlag & 0x800`, as per the spec.
-Otherwise, the file name is decoded with `ascii`, which is technically not correct.
-The correct default encoding is `cp473`.
+Following the spec, the bytes for the file name are decoded with
+`utf8` if `generalPurposeBitFlag & 0x800`, otherwise with `CP437`.
 
 #### extraFields
 
-`Array` with each entry in the form `{id: id, data: data}`, where `id` is a `Number` and `data` is a `Buffer`.
+`Array` with each entry in the form `{id: id, data: data}`,
+where `id` is a `Number` and `data` is a `Buffer`.
 None of the extra fields are considered significant by this library.
@@ -153,10 +171,7 @@
 
-### Default Charset Should Be CP437
-
-Currently, the default charset is `ascii`, but it should be `cp473`.
-
 ### No Multi-Disk Archive Support
 
 This library does not support multi-disk zip files.
-This API was intended for a zip file to span multiple floppy disks, which probably never happens now.
+The multi-disk fields in the zipfile spec were intended for a zip file to span multiple floppy disks,
+which probably never happens now.
 If the "number of this disk" field in the End of Central Directory Record is not `0`,
@@ -163,0 +178,0 @@ the `open` or `fopen` `callback` will receive an `err`.

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

No v1

Quality

Package is not semver >=1. This means it is not stable and does not support ^ ranges.

Found 1 instance in 1 package

Improved metrics

Lines of code

268

increased by3.88%

Number of low quality alerts

0

decreased by-100%

Number of lines in readme file

230

increased by6.98%

Worsened metrics

Total package byte prevSize

20236

decreased by-14.15%

Dependency count

3

increased by200%

Number of package files

5

decreased by-58.33%

Dependency changes

• + Addediconv@~2.1.4

• + Addedpend@~1.1.3

• + Addediconv@2.1.11(transitive)

• + Addednan@2.0.9(transitive)