Extraction from streams (#25)

Add the ! postfix operator and !! expression.
  Also add the ++ string concatenation operator.
  Also allow specification of standard input in the test scheme.

  Resolves #7, #18.

Co-authored-by: Glen Whitney <glen@studioinfinity.org>
Reviewed-on: #25
Co-Authored-By: Glen Whitney <glen@nobody@nowhere.net>
Co-Committed-By: Glen Whitney <glen@nobody@nowhere.net>

.drone.yml

@@ -29,7 +29,18 @@ steps:
       - java -jar /drone/lib/spt/org.metaborg.spt.cmd/target/org.metaborg.spt.cmd* -l . -s /drone/lib/spt/org.metaborg.meta.lang.spt -t tests
       - mkdir -p lib
       - curl -o lib/sunshine.jar -L 'http://artifacts.metaborg.org/service/local/artifact/maven/redirect?r=snapshots&g=org.metaborg&a=org.metaborg.sunshine2&v=LATEST'
-      - bin/fosgen tests/emit_sum.fos
+  - name: setup_gen
+    image: gcc
+    volumes:
+      - name: m2
+        path: /root/.m2
+    commands:
+      - git clone https://github.com/facebook/nailgun.git
+      - cd nailgun
+      - make
+      - cd ../bin
+      - ln -s ../nailgun/nailgun-client/target/ng .
+      - cd ..
   - name: extract_tests
     image: xonsh/xonsh
     commands:
@@ -41,7 +52,8 @@ steps:
         path: /drone/lib
       - name: m2
         path: /root/.m2
-    commands:
+    commands:  # Note we first make sure that fosgen is working
+      - bin/fosgen -d tests/emit_sum.fos
       - bin/generate_test_code
   - name: python_tests
     image: python:slim
@@ -55,6 +67,13 @@ steps:
     image: haskell
     commands:
       - bin/run_tests runghc hs
+  - name: ocaml_tests
+    image: ocaml/opam
+    commands:
+      - ls -als tests/extracted
+      - opam init
+      - eval $(opam env)
+      - bin/run_tests ocaml ml
 
 volumes:
   - name: lib

.gitignore

@@ -12,10 +12,16 @@
 
 .pydevproject
 
+a.out
+
 *.aterm
 /site
+bin/ng
 tests/extracted/*
 tests/*.js
 tests/*.py
 tests/*.hs
+tests/*.ml
+tests/*.cmi
+tests/*.cmo
 adhoc*

bin/extract_tests.xsh

@@ -13,12 +13,16 @@ DESTINATION = 'tests/extracted'
 # Extension for extracted files:
 EXT = 'fos'
 
+# Extension for desired input:
+INP = 'in'
+
 # Extension for expectations:
 EXP = 'expect'
 
 for path in TEST_LIST:
   destdir = pf"{DESTINATION}/{path.stem}"
   mkdir -p @(destdir)
+  chmod ugo+rwx @(destdir)
   contents = path.read_text()
   tests = re.split(r'test\s*(.+?)\s*\[\[.*?\n', contents)[1:]
   testit = iter(tests)
@@ -33,6 +37,11 @@ for path in TEST_LIST:
     expath = destdir / f"{name}.{EXT}"
     expath.write_text(example)
     echo Wrote @(expath)
+    im = re.search(r'/\*\*\s+accepts.*?\n([\s\S]*?)\*\*/', details[em.end():])
+    if im:
+      ipath = destdir / f"{name}.{INP}"
+      ipath.write_text(im[1])
+      echo "  ...and" @(ipath)
     xm = re.search(r'/\*\*\s+writes.*?\n([\s\S]*?)\*\*/', details[em.end():])
     if xm:
       xpath = destdir / f"{name}.{EXP}"

bin/fosgen

@@ -5,6 +5,7 @@ erro() { printf "%s\n" "$*" >&2; }
 
 ##### Set defaults:
 SUPPRESS_ERR=YES
+USE_NAILGUN=YES
 LANGUAGE=Python
 
 ##### Extract command line options:
@@ -14,18 +15,23 @@ do
     -h|--help)
       echo
       echo "Usage:"
-      echo "  fosgen [-d] [-l LANGUAGE] FILE"
+      echo "  fosgen [-d] [-j] [-l LANGUAGE] FILE"
       echo
       echo "Writes to standard output the code generated from the fostr"
       echo "program in FILE, targeting the specified LANGUAGE (which"
       echo "defaults to Python)."
       echo
       echo "The -d option writes diagnostic output to standard error."
+      echo "The -j option uses the Spoofax Sunshine JAR directly, rather"
+      echo "than via nailgun."
       exit
       ;;
     -d)
       SUPPRESS_ERR=''
       ;;
+    -j)
+      USE_NAILGUN=''
+      ;;
     -l)
       shift
       LANGUAGE="$1"
@@ -67,5 +73,17 @@ then
   exec 2>/dev/null
 fi
 
+if [[ $USE_NAILGUN ]]
+then
+  if [[ $SUPPRESS_ERR ]]
+  then
+    $BINDIR/let_sun_shine
+  else
+    $BINDIR/let_sun_shine noisy
+  fi
+  $BINDIR/ng sunshine transform -p $PROJDIR -n $LANGUAGE -i $PROGRAM
+  exit $?
+fi
+
 java -jar $SUNJAR transform -p $PROJDIR -l $PROJDIR -l $MVN_REPO -n $LANGUAGE -i $PROGRAM
 exit $?

bin/generate_test_code

@@ -4,7 +4,7 @@ failed=0
 
 for dir in tests/extracted/*; do
   for file in $dir/*.fos; do
-    for language in Python Javascript Haskell; do
+    for language in Python Javascript Haskell OCaml; do
       echo bin/fosgen -l ${language%.*} $file ...
       bin/fosgen -l $language $file
       if [[ $? -ne 0 ]]; then

bin/let_sun_shine

@@ -0,0 +1,40 @@
+#!/bin/bash
+
+# Helper for fosgen, not intended to be used directly
+# With an argument, print diagnostic output
+
+BINDIR=$(dirname $BASH_SOURCE)
+
+if $BINDIR/ng sunshine --help
+then
+  if [[ $1 ]]
+  then
+    echo "sun already shining."
+  fi
+else
+  if [[ $1 ]]
+  then
+    echo "disperse the clouds."
+  fi
+  SUNJAR="$BINDIR/../lib/sunshine.jar"
+  PROJDIR="$BINDIR/.."
+  if [[ ! $MVN_REPO ]]; then
+    MVN_REPO="$HOME/.m2/repository"
+  fi
+  if [[ ! -d $MVN_REPO ]]; then
+    MVN_REPO="/root/.m2/repository"
+  fi
+  if [[ ! -d $MVN_REPO ]]; then
+    echo "Cannot find your Maven repository. Please set environment variable"
+    echo "MVN_REPO to its full path and re-run."
+    exit 1
+  fi
+  if [[ $1 ]]
+  then 
+    java -jar $SUNJAR server & 
+  else
+    java -jar $SUNJAR server >/dev/null 2>&1 &
+  fi
+  sleep 5
+  $BINDIR/ng sunshine load -l $PROJDIR -l $MVN_REPO
+fi

bin/run_tests

@@ -9,8 +9,14 @@ diffed=0
 for dir in tests/extracted/*; do
   for file in $dir/*.$ext; do
     ((total++))
+    if [[ -f ${file%.*}.in ]]; then
+       cat ${file%.*}.in | $command $file > $file.out
+       result=$?
+    else
        $command $file > $file.out
-    if [[ $? -ne 0 ]]; then
+       result=$?
+    fi
+    if [[ $result -ne 0 ]]; then
       echo ERROR: $command $file failed.
       ((failed++))
     else

editor/Generation.esv

@@ -4,3 +4,4 @@ menus
     action: "Python"     = to-python
     action: "Javascript" = to-javascript
     action: "Haskell"    = to-haskell
+    action: "OCaml"      = to-ocaml

mkdocs.yml

@@ -9,7 +9,7 @@ plugins:
 - search
 - semiliterate:
     ignore_folders: [target, lib]
-    exclude_extensions: ['.o', '.hi']
+    exclude_extensions: ['.o', '.hi', '.cmi', '.cmo']
     extract_standard_markdown:
       terminate: <!-- /md -->
 theme:

syntax/fostr.sdf3

@@ -42,10 +42,13 @@ context-free syntax
   Ex.EscString = STRING
   Ex.Stream    = <stream>
   Ex.Sum       = <<Ex> +  <Ex>> {left}
+  Ex.Concat    = <<Ex> ++ <Ex>> {left}
   Ex.Gets      = [[Ex] << [Ex]] {left}
   Ex.DefGets   = [<<< [Ex]]
   Ex.To        = [[Ex] >> [Ex]] {left}
   Ex.DefTo     = [[Ex] >>>]
+  Ex.Emits     = <<Ex>!>
+  Ex.DefEmits  = <!!>
 
   Ex           = <(<Ex>)> {bracket}
 
@@ -53,7 +56,7 @@ context-free priorities
 
   Ex.To
   > Ex.DefTo
-  > Ex.Sum
+  > {Ex.Sum Ex.Concat}
   > Ex.DefGets
   > Ex.Gets,
 

tests/basic.spt

@@ -59,8 +59,8 @@ For example, this snippet generates the following Python:
 It generates nearly identical code in
 this simple example for Javascript (just with `"Hello, world!"`
 in place of `r'Hello, world!'`), although it generates a different
-preamble defining Stdio for each language. (Currently, Haskell code
-generation is also supported.)
+preamble defining Stdio for each language. (Currently, Haskell and OCaml
+code generation are also supported.)
 
 There's not much to break down in such a tiny program as this, but let's do
 it. The prefix operator `<<<` could be read as "the default stream receives...",
@@ -108,7 +108,7 @@ again. That way we can use the general (left-associative)
 parse to TopLevel(
   Gets(Gets(Gets(Gets(DefGets(LitString("'Two and '")),Int("2")),
                  LitString("' make '")),Sum(Int("2"),Int("2"))),
-       EscString("\"./n\"")))
+       EscString("\".\n\"")))
 /** writes
 Two and 2 make 4.
 **/
@@ -293,4 +293,38 @@ test emit_several_default [[
                 >>>
 ]] parse succeeds
 /** writes
-3399677527121313*/
+3399677527121313**/
+
+/** md
+### Streams are bidirectional
+
+So far we have only sent items to a stream. But we can extract them from
+streams as well, with the `!` postfix operator. `!!` all by itself abbreviates
+`stream!`, i.e., extraction from the standard stream. For example,
+
+```fostr
+**/
+
+/** md */ test custom_hw [[
+<<< "What is your name?\n"
+<<< 'Hello, ' ++ !!
+]] /* **/
+parse to TopLevel(Sequence([
+  DefGets(EscString("\"What is your name?\n\"")),
+  DefGets(Concat(LitString("'Hello, '"),DefEmits()))
+]))
+/** accepts
+Kilroy
+**/
+/** writes
+What is your name?
+Hello, Kilroy
+**/
+
+/** md
+```
+
+queries users for their name and then writes a customized greeting. It also
+illustrates the use of `++` for string concatenation, as opposed to `+` for
+(numerical) addition.
+**/

trans/desugar.str

@@ -17,6 +17,7 @@ rules
   
   defStream:  DefGets(x)  -> Gets(Stream(), x)
   defStream:  DefTo(x)    -> To(x, Stream())
+  defStream:  DefEmits()  -> Emits(Stream())
 
 strategies
 

trans/fostr.str

@@ -6,6 +6,7 @@ imports
   pp
   outline
   analysis
+  ocaml
   haskell
   javascript
   python

trans/haskell.str

@@ -10,7 +10,7 @@ rules
         rule.
      C) We will use bottomup-para to traverse the full AST with the
         transformation from A so that we have access to the original expression
-        (and get get the Statix-associated type when we need to).
+        (and can get the Statix-associated type when we need to).
         Hence the transformation in (A) must actually take a pair of
         an (original) term and a term with value strings at each child,
         and be certain to return a value string.
@@ -23,6 +23,7 @@ rules
   import System.IO
   data IOStream = StdIO
 
+  -- Danger: These currently assume the stream is StdIO
   gets :: Show b => a -> b -> IO a
   gets s d = do
     putStr(show d)
@@ -33,6 +34,10 @@ rules
     putStr(d)
     return s
 
+  emit s = do
+    l <- getLine
+    return (l ++ "\n")
+
   main = do
     [<Preactions>()]return [val]]
 
@@ -41,6 +46,7 @@ rules
   hs: (_, LitString(x)) -> <haskLitString>x
   hs: (_, EscString(x)) -> x
   hs: (_, Sum(x, y))    -> $[([x] + [y])]
+  hs: (_, Concat(x, y)) -> $[([x] ++ [y])]
 
   hs: (Gets(_, xn), Gets(s, x)) -> v
     with v := <newname>"_fostr_get"
@@ -52,6 +58,10 @@ rules
   hs_gets: (s, xn, x ) -> $[[s] [<hs_getOp>xn] [x]]
   hs_getOp = get-type; (?STRING() < !"`getsStr`" + !"`gets`")
 
+  hs: (_, Emits(s)) -> v
+    with v := <newname>"_fostr_emitted"
+       ; <add-preactions>[$[[v] <- emit [s]]]
+
   hs: (_, Terminate(x)) -> $[[x];;]
   hs: (_, Sequence(l))  -> <last>l
   /* One drawback of using paramorphism is we have to handle lists

trans/javascript.str

@@ -3,24 +3,41 @@ imports libstrategolib signatures/- util
 
 rules
   js: TopLevel(x) -> $[// Fostr preamble
+  const _fostr_readline = require('readline');
+  const _fostr_events = require('events');
+  const _fostr_rl = _fostr_readline.createInterface({input: process.stdin});
   const Stdio = {
     gets:  v => { process.stdout.write(String(v)); return Stdio; },
+    emit: async () => {
+            const [line] = await _fostr_events.once(_fostr_rl, 'line');
+            return line + "\n"; }
   }
   function to(data, strm) {
     strm.gets(data);
     return data;
   }
+
+  const _fostr_body = async () => {
   // End of preamble
 
-  [x]]
+    [x]
+
+  // Fostr coda
+    _fostr_rl.close()
+  }
+  _fostr_body();
+  ]
+    with line := "[line]"
 
   js: Stream()     -> $[Stdio]
   js: Int(x)       -> x
   js: LitString(x) -> <javaLitString>x
   js: EscString(x) -> x
   js: Sum(x, y)    -> $[[x] + [y]]
+  js: Concat(x, y) -> $[[x] + [y]]
   js: Gets(x, y)   -> $[[x].gets([y])]
   js: To(x, y)     -> $[to([x],[y])]
+  js: Emits(x)     -> $[(await [x].emit())]
   js: Terminate(x) -> x
   js: Sequence(l)  -> <join(|";\n")>l
 

trans/ocaml.str

@@ -0,0 +1,66 @@
+module ocaml
+imports libstrategolib signatures/- util signature/TYPE analysis
+
+/* Note will use bottomup-para to traverse the full AST so that
+   we have access to the original expression (and can get the
+   Statix-associated type when we need to).
+   
+   This means that every one of our local rules must take a pair
+   of an original term and a term with every child replaced by
+   its generated code.
+ */
+
+rules
+  ml: (_, TopLevel(x)) -> $[(* fostr preamble *)
+  type stream = { getS: string -> stream; emitS: unit -> string }
+  let rec stdio = {
+    getS = (fun s -> print_string s; stdio);
+    emitS = (fun () -> (read_line ()) ^ "\n");
+  };;
+  (* End of preamble *)
+
+  [x]]
+
+  ml: (_, Stream())     -> $[stdio]
+  ml: (_, Int(x))       -> x
+  ml: (_, LitString(x)) -> $[{|[<un-single-quote>x]|}]
+  ml: (_, EscString(x)) -> x
+  ml: (_, Sum(x, y))    -> $[[x] + [y]]
+  ml: (_, Concat(x, y)) -> $[[x] ^ [y]]
+
+  ml: (Gets(_,yn), Gets(x, y))
+    -> $[([x]).getS ([<ml_str>(yn,y)])]
+  ml: (To(xn,_),   To(x, y))
+    -> $[let _fto = ([x]) in (ignore (([y]).getS ([<ml_str>(xn,"_fto")])); _fto)]
+  ml: (_, Emits(s))     -> $[[s].emitS ()]
+
+  ml: (_, Terminate(x)) -> x
+  ml: (_, Sequence(l))  -> <ml_seq>l
+  
+  ml_seq: [x] -> x
+  ml_seq: [x | xs ] -> $[ignore ([x]);
+[<ml_seq>xs]]
+
+  /* One drawback of using paramorphism is we have to handle lists
+     explicitly:
+   */
+  ml: (_, []) -> []
+  ml: (_, [x | xs]) -> [x | xs]
+
+  /* Another drawback of using paramorphism is at the very leaves we have
+     to undouble the tuple:
+   */
+  ml: (x, x) -> x where <is-string>x
+
+  ml_str: (node, code) -> $[[<ml_string_cast>node]([code])]
+
+strategies
+
+  ml_string_cast = get-type; (?INT() < !"string_of_int" + !"")
+
+  ocaml = bottomup-para(try(ml))
+
+  // Interface ocaml code generation with editor services and file system
+  to-ocaml: (selected, _, _, path, project-path) -> (filename, result)
+    with filename := <guarantee-extension(|"ml")> path
+       ; result   := <ocaml> selected

trans/python.str

@@ -8,6 +8,8 @@ rules
     def gets(self, v):
       print(v, file=sys.stdout, end='')
       return self
+    def emit(self):
+      return input() + "\n" # Python inconsistently strips when using input
   def to(data,strm):
     strm.gets(data)
     return data
@@ -21,8 +23,10 @@ rules
   py: LitString(x) -> $[r[x]]
   py: EscString(x) -> x
   py: Sum(x,y)     -> $[[x] + [y]]
+  py: Concat(x,y)  -> $[[x] + [y]]
   py: Gets(x, y)   -> $[[x].gets([y])]
   py: To(x, y)     -> $[to([x],[y])]
+  py: Emits(x)     -> $[[x].emit()]
   py: Terminate(x) -> $[[x];]
   py: Sequence(l)  -> <join(|"\n")>l
 

trans/statics.stx

@@ -222,6 +222,13 @@ This pattern lets us specify error messages.
     type_Ex(e2) == STREAM() | error $[Items may only be sent to Streams.]@e2.
   /* **/
 
+  ty_Ex(Concat(e1, e2)) = STRING() :-
+    type_Ex(e1) == STRING() | error $[Expression [e1] not String in concat.]@e1,
+    type_Ex(e2) == STRING() | error $[Expression [e2] not String in concat.]@e2.
+
+  ty_Ex(Emits(e)) = STRING() :- // At the moment, only stream is stdio
+    type_Ex(e) == STREAM() | error $[Only Streams may emit items.]@e.
+
   /** md
 ```