git.net

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[GitHub] mbeckerle commented on a change in pull request #61: Preliminary Review - Base64 layering runs first parsing unit test.


mbeckerle commented on a change in pull request #61: Preliminary Review - Base64 layering runs first parsing unit test.
URL: https://github.com/apache/incubator-daffodil/pull/61#discussion_r184977533
 
 

 ##########
 File path: daffodil-io/src/main/scala/org/apache/daffodil/io/LimitingJavaIinputStreams.scala
 ##########
 @@ -0,0 +1,287 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.daffodil.io
+
+import org.apache.daffodil.exceptions.Assert
+import java.util.regex.Pattern
+import java.util.Scanner
+import java.nio.charset.Charset
+import java.io.InputStream
+import java.io.FilterInputStream
+import java.io.InputStreamReader
+import java.nio.charset.StandardCharsets
+
+/**
+ * This class can be used with any InputStream to restrict what is
+ * read from it to N bytes.
+ *
+ * This can be used to forcibly stop consumption of data from a stream at
+ * a length obtained explicitly.
+ *
+ * Thread safety: This is inherently stateful - so not thread safe to use
+ * this object from more than one thread.
+ */
+class ExplicitLengthLimitingStream(in: InputStream, limit: Int)
+  extends FilterInputStream(in) {
+
+  private var numRemaining = limit
+
+  override def read(buf: Array[Byte], off: Int, len: Int) = {
+    Assert.invariant(numRemaining >= 0)
+    if (numRemaining == 0) -1
+    else if (len == 0) 0
+    else {
+      val requestSize = math.min(numRemaining, len)
+      val actualSize = in.read(buf, off, requestSize)
+      if (actualSize == -1)
+        numRemaining = 0
+      else
+        numRemaining -= actualSize
+      actualSize
+    }
+  }
+
+  private val readBuf = new Array[Byte](1)
+
+  override def read(): Int = {
+    readBuf(0) = 0
+    val n = read(readBuf, 0, 1)
+    if (n == -1)
+      -1
+    else {
+      Assert.invariant(n == 1)
+      val i = readBuf(0).toInt
+      val b = i & 0xFF
+      b
+    }
+  }
+}
+
+/**
+ * Can be used with any InputStream to restrict what is
+ * read from it to stop before a boundary mark string.
+ *
+ * The boundary mark string is exactly that, a string of characters. Not a
+ * regex, nor anything involving DFDL Character Entities or Character Class
+ * Entities. (No %WSP; no %NL; )
+ *
+ * This can be used to forcibly stop consumption of data from a stream at
+ * a length obtained from a delimiter.
+ *
+ * The boundary mark string is consumed from the underlying stream (if found), and
+ * the underlying stream is left positioned at the byte after the boundary mark
+ * string.
+ *
+ * Thread safety: This is inherently stateful - so not thread safe to use
+ * this object from more than one thread.
+ */
+object BoundaryMarkLimitingStream {
+
+  def apply(inputStream: InputStream, boundaryMark: String, charset: Charset,
+    targetChunkSize: Int = 32 * 1024) = {
+
+    Assert.usage(targetChunkSize >= 1)
+    Assert.usage(boundaryMark.length >= 1)
+
+    val boundaryMarkIn8859 = new String(boundaryMark.getBytes(charset), StandardCharsets.ISO_8859_1)
+
+    val quotedBoundaryMark = Pattern.quote(boundaryMarkIn8859) // in case pattern has non-regex-safe characters in it
+
+    val result = new RegexLimitingStream(inputStream, quotedBoundaryMark, boundaryMarkIn8859, charset, targetChunkSize)
+    result
+  }
+
+}
+
+class StreamIterator[T](s: Stream[T])
+  extends Iterator[T] {
+  private var str = s
+  override def hasNext = !str.isEmpty
+  override def next() = {
+    val res = str.head
+    str = str.tail
+    res
+  }
+}
+
+/**
+ * Can be used with any InputStream to restrict what is
+ * read from it to stop before a particular regex match.
+ *
+ * The regex must have a finite maximum length match string.
+ *
+ * This can be used to forcibly stop consumption of data from a stream at
+ * a length obtained from a delimiter that is described using a regex.
+ *
+ * The delimiter matching the regex is consumed from the underlying stream (if found), and
+ * the underlying stream is left positioned at the byte after the regex match
+ * string.
+ *
+ * IMPORTANT: The delimiter regex cannot contain any Capturing Groups!
 
 Review comment:
   Hi Taylor, no nothing checks this as yet. It is possible to check, as regex are checkable that way, but it's non-trivial.  I'm thinking a comment should be sufficient. It's not like this string gets passed in from a user schema. 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@xxxxxxxxxxxxxxxx


With regards,
Apache Git Services