Fix beauitfulsoup issue and add config path

spencerwuwu · spencerwuwu · commit 463f0fe0a3d3 · 2017-07-26T13:32:24.000+08:00
Fix beauitfulsoup issue and add config path

Fix beauitfulsoup issue and add config path
diff --git a/.gitignore b/.gitignore
@@ -1,5 +1,5 @@
 biglambda/producers/parser.out
 biglambda/producers/typetab.py
-biglambda/producers/__pycache__
-biglambda/consumers/__pycache__
-biglambda/__pycache__
+__pycache__
+.python-version
+setup.pyc
diff --git a/README.md b/README.md
@@ -1,5 +1,29 @@
 # biglambda
-Source code for the BigLambda data-parallel synthesis project. Based on the PLDI 2016 paper **MapReduce Program Synthesis** by [Calvin Smith](http://pages.cs.wisc.edu/~cjsmith/) and [Aws Albarghouthi](http://pages.cs.wisc.edu/~aws/).
+Source code for the BigLambda data-parallel synthesis project. Based 
+on the PLDI 2016 paper **MapReduce Program Synthesis** by 
+[Calvin Smith](http://pages.cs.wisc.edu/~cjsmith/) and 
+[Aws Albarghouthi](http://pages.cs.wisc.edu/~aws/).
 
 ## Dependencies
-The tool depends on the most recent versions of `BeautifulSoup` and `ply`, neither of which are included.
+The tool depends on the most recent versions of `BeautifulSoup`,
+`lxml`, and `ply`, neither of which are included.
+
+## Usage
+First edit `PATH` in `biglambda/setup.py`.
+```
+usage: BigLambda - synthesizing MapReduce programs since 2015
+       [-h] [-s SIGNATURE] [-d DATA] [-v] [-fs FRONTIERSIZE] [-p] [--dinner]
+       [-b BENCHMARK]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -s SIGNATURE, --signature SIGNATURE
+  -d DATA, --data DATA
+  -v, --verbose
+  -fs FRONTIERSIZE, --frontiersize FRONTIERSIZE
+  -p, --parallel
+  --dinner
+  -b BENCHMARK, --benchmark BENCHMARK
+```
+`biglambda/producers/parser.out` and `biglambda/producers/typetab.py` 
+will be generated after the computation.
diff --git a/benchmarks/anagram/data b/benchmarks/anagram/data
@@ -1,8 +1,8 @@
 <data input="String" output="[String]" key="String">
-    <norm name="append" tag="assoc">
-    <weight name="emit" val=0.001>
-    <weight name="sort_word" val=2>
-    <weight name="to_chars" val=0.1>
+    <norm name="append" tag="assoc" />
+    <weight name="emit" val="0.001" />
+    <weight name="sort_word" val="2" />
+    <weight name="to_chars" val="0.1" />
     <example>
         <input delim=","> "banana aaabnn test", "estt ananab" </input>
         <output>
diff --git a/benchmarks/average/data b/benchmarks/average/data
@@ -1,10 +1,10 @@
 <data input="Int" key="Int" output="Float">
     <example>
         <input delim=","> 1, 2, 3 </input>
-        <output val=2.0 />
+        <output val="2.0" />
     </example>
     <example>
         <input delim=","> 0, 5 </input>
-        <output val=2.5 />
+        <output val="2.5" />
     </example>
 </data>
diff --git a/benchmarks/cycling_bpm/data b/benchmarks/cycling_bpm/data
@@ -1,8 +1,8 @@
 <data input="Record" key="Int" output="Int">
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
-    <weight name="emit" val=0.0001>
-    <weight name="one" val=0.1>
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
+    <weight name="emit" val="0.0001" />
+    <weight name="one" val="0.1" />
     <example>
         <input>
             (212956, 218, 79, 6.991)
diff --git a/benchmarks/cycling_speed/data b/benchmarks/cycling_speed/data
@@ -1,8 +1,8 @@
 <data input="Record" key="Int" output="Int">
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
-    <weight name="emit" val=0.0001>
-    <weight name="speed" val=100>
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
+    <weight name="emit" val="0.0001" />
+    <weight name="speed" val="100" />
     <example>
         <input>
             (212956, 218, 79, 6.991)
diff --git a/benchmarks/cycling_watts/data b/benchmarks/cycling_watts/data
@@ -1,8 +1,8 @@
 <data input="Record" key="Int" output="Int">
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
-    <weight name="emit" val=0.0001>
-    <weight name="one" val=0.1>
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
+    <weight name="emit" val="0.0001" />
+    <weight name="one" val="0.1" />
     <example>
         <input>
             (212956, 218, 79, 6.991)
diff --git a/benchmarks/dateextraction/data b/benchmarks/dateextraction/data
@@ -1,6 +1,6 @@
 <data input="String" output="[String]">
-    <norm name="append" tag="assoc">
-    <weight name="extract" val=100>
+    <norm name="append" tag="assoc" />
+    <weight name="extract" val="100" />
     <example>
         <input>
             "There will be a meeting at DATE01, and maybe DATE02"
diff --git a/benchmarks/factorcounting/data b/benchmarks/factorcounting/data
@@ -1,7 +1,7 @@
 <data input="Int" output="Int" key="Int">
-    <norm name="plus" tag="ac">
-    <weight name="factor" val=10>
-    <weight name="emit" val=0.01>
+    <norm name="plus" tag="ac" />
+    <weight name="factor" val="10" />
+    <weight name="emit" val="0.01" />
     <example>
         <input delim=","> 2, 3, 4 </input>
         <output>
diff --git a/benchmarks/grep/data b/benchmarks/grep/data
@@ -1,5 +1,5 @@
 <data input="String" output="[String]">
-    <weight name="core_filter" val=100>
+    <weight name="core_filter" val="100" />
     <example>
         <input delim=","> "That dog there", "what a human cat" </input>
         <output delim=","> "dog", "human", "cat" </output>
diff --git a/benchmarks/histogram/data b/benchmarks/histogram/data
@@ -1,6 +1,6 @@
 <data input="Float" output="Int" key="Sign">
-    <norm name="plus" tag="ac">
-    <norm name="fplus" tag="ac">
+    <norm name="plus" tag="ac" />
+    <norm name="fplus" tag="ac" />
     <example>
         <input delim=","> 0.0, 0.1, -0.1 </input>
         <output>
diff --git a/benchmarks/join/data b/benchmarks/join/data
@@ -1,8 +1,8 @@
 <data input="Database" key="String" output="[Item]">
-    <weight name="access" val=10>
-    <weight name="filt" val=0.01>
-    <weight name="concat_db" val=0.01>
-    <weight name="VALUE" val=0.01>
+    <weight name="access" val="10" />
+    <weight name="filt" val="0.01" />
+    <weight name="concat_db" val="0.01" />
+    <weight name="VALUE" val="0.01" />
     <example>
         <input>
             ("DB0", [("K0", "V0"), ("K2", "V2")])
diff --git a/benchmarks/letteranalysis/data b/benchmarks/letteranalysis/data
@@ -1,7 +1,7 @@
 <data input="String" output="Int" key="String">
-    <norm name="add" tag="ac">
-    <norm name="lower" tag="idem">
-    <weight name="lower" val=10>
+    <norm name="add" tag="ac" />
+    <norm name="lower" tag="idem" />
+    <weight name="lower" val="10" />
     <example>
         <input delim=","> "Aaa", "bb", "c" </input>
         <output>
diff --git a/benchmarks/max/data b/benchmarks/max/data
@@ -1,17 +1,17 @@
 <data input="Int" output="Int">
-    <norm name="splus" tag="ac">
-    <norm name="smin" tag="comm">
-    <norm name="smax" tag="comm">
+    <norm name="splus" tag="ac"></norm>
+    <norm name="smin" tag="comm"></norm>
+    <norm name="smax" tag="comm"></norm>
     <example>
         <input delim=",">1,2,3,4</input>
-        <output val=4>
+        <output val="4"/>
     </example>
     <example>
         <input delim=",">4,3,1,2</input>
-        <output val=4>
+        <output val="4"/>
     </example>
     <example>
         <input delim=",">100, 200, 201, 101, 99</input>
-        <output val=201>
+        <output val="201"/>
     </example>
 </data>
diff --git a/benchmarks/min/data b/benchmarks/min/data
@@ -1,14 +1,14 @@
 <data input="Int" output="Int">
     <example>
         <input delim=",">1,2,3,4</input>
-        <output val=1>
+        <output val="1" />
     </example>
     <example>
         <input delim=",">4,3,1,2</input>
-        <output val=1>
+        <output val="1" />
     </example>
     <example>
         <input delim=",">100, 200, 201, 101, 99</input>
-        <output val=99>
+        <output val="99" />
     </example>
 </data>
diff --git a/benchmarks/mss/data b/benchmarks/mss/data
@@ -1,5 +1,5 @@
 <data input="[Int]" key="Int" output="[Int]">
-    <weight name="map_reduce_keyed_emit_map" val=1000>
+    <weight name="map_reduce_keyed_emit_map" val="1000" />
     <example>
         <input>
             [-2, 1, -3, 4, -1, 2, 1, -5, 4]
diff --git a/benchmarks/postagging/data b/benchmarks/postagging/data
@@ -1,5 +1,5 @@
 <data input="String" output="Int" key="Tag">
-    <norm name="plus" tag="ac">
+    <norm name="plus" tag="ac" />
     <example>
         <input delim=","> "This is a test", "fluffy cat play" </input>
         <output>
diff --git a/benchmarks/roundedsum/data b/benchmarks/roundedsum/data
@@ -1,10 +1,10 @@
 <data input="Float" output="Int">
     <example>
         <input delim=","> 1.3, 2.1, 3.2 </input>
-        <output val=6 />
+        <output val="6" />
     </example>
     <example>
         <input delim=","> 1.0, 2.1, 5.3 </input>
-        <output val=8 />
+        <output val="8" />
     </example>
 </data>
diff --git a/benchmarks/selection/data b/benchmarks/selection/data
@@ -1,8 +1,8 @@
 <data input="Database" output="[Item]">
-    <weight name="KEY" val=10>
-    <weight name="VALUE" val=10>
-    <weight name="m" val=0.01>
-    <weight name="filt" val=10>
+    <weight name="KEY" val="10" />
+    <weight name="VALUE" val="10" />
+    <weight name="m" val="0.01" />
+    <weight name="filt" val="10" />
     <example>
         <input>
             ("DB1", [("K0", "V0"), ("K1", "V0")])
diff --git a/benchmarks/shakespeare_chars/data b/benchmarks/shakespeare_chars/data
@@ -1,9 +1,9 @@
 <data input="String" key="String" output="Int">
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
-    <weight name="add" val=0.5>
-    <weight name="iscaps" val=10>
-    <weight name="issentiment" val=0.1>
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
+    <weight name="add" val="0.5" />
+    <weight name="iscaps" val="10" />
+    <weight name="issentiment" val="0.1" />
     <example>
         <input>
             "HELENA	What is your pleasure, madam?"
diff --git a/benchmarks/shakespeare_sentiment/data b/benchmarks/shakespeare_sentiment/data
@@ -1,7 +1,7 @@
 <data input="String" key="String" output="Int">
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
-    <weight name="add" val=0.5>
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
+    <weight name="add" val="0.5" />
     <example>
         <input>
             "HELENA	What is your pleasure, madam?"
diff --git a/benchmarks/squaredsum/data b/benchmarks/squaredsum/data
@@ -1,13 +1,13 @@
 <data input="Int" output="Int">
-    <norm name="add" tag="ac">
-    <norm name="fadd" tag="ac">
+    <norm name="add" tag="ac" />
+    <norm name="fadd" tag="ac" />
     <example>
         <input delim=",">1, 2, 3</input>
-        <output val=14>
+        <output val="14" />
     </example>
     <example>
         <input delim=",">7, 0, 5</input>
-        <output val=74>
+        <output val="74" />
     </example>
 </data>
 <trs>
@@ -21,4 +21,4 @@
         fadd(fadd(1, 2), 3) -> fadd(1, fadd(2, 3))
         round(cast(1)) -> 1
     </rules>
-</trs>
+</trs>
diff --git a/benchmarks/sum/data b/benchmarks/sum/data
@@ -1,13 +1,13 @@
 <data input="Int" output="Int">
-    <weight name="add" val="100">
-    <norm name="add" tag="ac">
+    <weight name="add" val="100" />
+    <norm name="add" tag="ac" />
     <example>
         <input delim=",">1,2,3</input>
-        <output val=6>
+        <output val="6"/>
     </example>
     <example>
         <input delim=",">4,5,6</input>
-        <output val=15>
+        <output val="15"/>
     </example>
 </data>
 <trs>
@@ -21,4 +21,4 @@
         fadd(fadd(1, 2), 3) -> fadd(1, fadd(2, 3))
         round(cast(1)) -> 1
     </rules>
-</trs>
+</trs>
diff --git a/benchmarks/sumoffactors/data b/benchmarks/sumoffactors/data
@@ -1,12 +1,12 @@
 <data input="Int" output="Int">
-    <norm name="plus" tag="ac">
-    <weight name="map_reduce_emit" val=100>
+    <norm name="plus" tag="ac" />
+    <weight name="map_reduce_emit" val="100" />
     <example>
         <input delim=","> 2, 3, 4 </input>
-        <output val=7 />
+        <output val="7" />
     </example>
     <example>
         <input delim=","> 5, 6, 35, 16 </input>
-        <output val=24 />
+        <output val="24" />
     </example>
 </data>
diff --git a/benchmarks/sumrounded/data b/benchmarks/sumrounded/data
@@ -1,10 +1,10 @@
 <data input="Float" output="Int">
     <example>
         <input delim=","> 1.1, 2.1, 3.1 </input>
-        <output val=6 />
+        <output val="6" />
     </example>
     <example>
         <input delim=","> 1.4, 2.5, 3.3 </input>
-        <output val=7 />
+        <output val="7" />
     </example>
 </data>
diff --git a/benchmarks/sumsquared/data b/benchmarks/sumsquared/data
@@ -1,15 +1,15 @@
 <data input="Int" output="Int">
     <example>
         <input delim=","> 1, 2, 3 </input>
-        <output val=36 />
+        <output val="36" />
     </example>
     <example>
         <input delim=","> 0, 2 </input>
-        <output val=4 />
+        <output val="4" />
     </example>
     <example>
         <input delim=","> 7, 0, 5 </input>
-        <output val=144 />
+        <output val="144" />
     </example>
 </data>
 <trs>
@@ -37,4 +37,4 @@
         fadd(1, 2) == fadd(2, 1)
         fadd(1, fadd(2, 3)) == fadd(3, fadd(1, 2))
     </eqs>
-</trs>
+</trs>
diff --git a/benchmarks/twitter_counts/data b/benchmarks/twitter_counts/data
@@ -1,7 +1,7 @@
 <data input="String" output="Int" key="String">
-    <weight name="find_matches" val=100>
-    <weight name="fst" val=0.0001>
-    <weight name="snd" val=0.0001>
+    <weight name="find_matches" val="100" />
+    <weight name="fst" val="0.0001" />
+    <weight name="snd" val="0.0001" />
     <example>
         <input>
             "retweet #foo #bar"
diff --git a/benchmarks/twitter_pairs/data b/benchmarks/twitter_pairs/data
diff --git a/benchmarks/unique/data b/benchmarks/unique/data
diff --git a/benchmarks/wiki_counts/data b/benchmarks/wiki_counts/data
diff --git a/benchmarks/wordcount/data b/benchmarks/wordcount/data
diff --git a/benchmarks/yelp_kids/data b/benchmarks/yelp_kids/data
diff --git a/biglambda/__main__.py b/biglambda/__main__.py
diff --git a/biglambda/setup.py b/biglambda/setup.py
