refining --only-code-output

Author: gpoore

CHANGELOG.md

@@ -3,6 +3,11 @@
 
 ## v0.7.0 (dev)
 
+* Added `--only-code-output` option, which writes code output in JSON Lines
+  format to stdout as soon as it is available, and does not create a document.
+  This is intended for use with Codebraid Preview, so that document previews
+  can be updated during code execution.
+
 * Added command-line option `--no-execute` that disables code execution and
   only uses available cached output.
 

README.md

@@ -216,6 +216,22 @@ needed in Markdown documents, this can be accomplished by piping the output of
 
 * `--no-execute` — Disables code execution.  Only use available cached output.
 
+* `--only-code-output`={format} — Write code output in JSON Lines format to
+  stdout as soon as it is available, and do not create a document.
+
+  This is intended for use with Codebraid Preview, so that document previews
+  can be updated during code execution.  Currently, the only supported format
+  is `codebraid_preview`.  One JSON data object followed by a newline is
+  written to stdout for each code chunk.  In some cases, the data for a chunk
+  will be resent later if the data relevant for a chunk changes (for example,
+  if code execution fails after the first chunk runs, but in such a way that
+  an error message needs to be attached to the first chunk).  Data for a chunk
+  is sent as soon as it is available from code processing, from cache, or from
+  code execution (as soon as the chunk completes, typically before the session
+  completes).  Additional JSON data may be sent to provide tracking of code
+  execution progress or information such as metadata.  The JSON data provided
+  for format `codebraid_preview` may change between minor versions.
+
 
 ## Caching
 

codebraid/cmdline.py

@@ -12,7 +12,6 @@
 
 
 import argparse
-import codecs
 import io
 import pathlib
 import sys
@@ -128,7 +127,7 @@ def print_help(self):
 
 def pandoc(args):
     # Stay consistent with Pandoc's requirement of UTF-8
-    sys.stdin = codecs.getreader('utf_8_sig')(sys.stdin.buffer, 'strict')
+    sys.stdin = io.TextIOWrapper(sys.stdin.buffer, encoding='utf_8_sig')
 
     other_pandoc_args = []
     if vars(args).get('--defaults') is not None:

codebraid/converters/pandoc.py

@@ -344,9 +344,12 @@ def __init__(self,
     def attr_hash(self):
         attr_list = []
         attr_list.append('{')
-        attr_list.append(f'#{self.node_id}')
+        if self.node_id:
+            attr_list.append(f'#{self.node_id}')
         attr_list.extend(f'.{c}' for c in self.node_classes)
-        attr_list.extend('"{0}"="{1}"'.format(k.replace('"', '\\"'), v.replace('"', '\\"')) for k, v in self.node_kvpairs)
+        for k, v in self.node_kvpairs:
+            v = v.replace('\\', '\\\\').replace('"', '\\"')
+            attr_list.extend(f'{k}="{v}"')
         attr_list.append('}')
         attr_str = ' '.join(attr_list)
         hasher = hashlib.sha1()
@@ -760,7 +763,7 @@ def _as_markdown_attr(self,
     def _as_markdown_inline_code(self, text: str, *, id=None, classes=None, keyval=None, raw=None, protect_start=True):
         md_list = []
         if protect_start:
-            md_list.append('[]{.codebraid-protect-inline-start}')
+            md_list.append('[]{.codebraid-protect-inline=true}')
         delim = '`'
         while delim in text:
             delim += '`'

codebraid/progress.py

@@ -15,6 +15,7 @@
 import collections
 import datetime
 import json
+import sys
 import time
 import textwrap
 from typing import Callable, Deque, Dict, Iterable, List, Optional
@@ -328,14 +329,16 @@ def _print_live_output(self, output: str, *, stream: str, fmter: Optional[Callab
 
 
     def _print_code_output(self, code_collection: CodeCollection, *, chunk: CodeChunk, check_first_chunk=False):
-        type = code_collection.type
-        lang = chunk.options.get('placeholder_lang', chunk.options['lang'] or '')
-        name = code_collection.name or ''
         data = {
-            'command': 'output',
-            'key': f'{type}>{lang}>{name}',
+            'message_type': 'output',
+            'origin': chunk.origin_name or '',
+            'code_collection': {
+                'type': code_collection.type,
+                'lang': chunk.options.get('placeholder_lang', chunk.options['lang'] or ''),
+                'name': code_collection.name or '',
+            },
             'inline': chunk.inline,
-            'index': f'{chunk.index+1}/{len(code_collection.code_chunks)}',
+            'number': f'{chunk.index+1}/{len(code_collection.code_chunks)}',
             'attr_hash': chunk.attr_hash,
             'code_hash': chunk.code_hash,
             'output': chunk.only_code_output(self._only_code_output),
@@ -346,7 +349,10 @@ def _print_code_output(self, code_collection: CodeCollection, *, chunk: CodeChun
                 return
         elif chunk.index == 0:
             self._only_code_output_first_chunk_cache[code_collection.key] = data
-        print(json.dumps(data), flush=True)
+        # All data I/O must be UTF-8, following Pandoc
+        sys.stdout.buffer.write(json.dumps(data).encode('utf8'))
+        sys.stdout.buffer.write(b'\n')
+        sys.stdout.buffer.flush()
 
 
     def _update_message_count(self, code_collection: CodeCollection):

codebraid/version.py

@@ -1,4 +1,4 @@
 # -*- coding: utf-8 -*-
 
 from .fmtversion import get_version_plus_info
-__version__, __version_info__ = get_version_plus_info(0, 7, 0, 'dev', 3)
+__version__, __version_info__ = get_version_plus_info(0, 7, 0, 'dev', 4)