summaryrefslogtreecommitdiffstats
path: root/python/pyyaml/examples/pygments-lexer
diff options
context:
space:
mode:
authorMatt A. Tobin <mattatobin@localhost.localdomain>2018-02-02 04:16:08 -0500
committerMatt A. Tobin <mattatobin@localhost.localdomain>2018-02-02 04:16:08 -0500
commit5f8de423f190bbb79a62f804151bc24824fa32d8 (patch)
tree10027f336435511475e392454359edea8e25895d /python/pyyaml/examples/pygments-lexer
parent49ee0794b5d912db1f95dce6eb52d781dc210db5 (diff)
downloadUXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.gz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.lz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.xz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.zip
Add m-esr52 at 52.6.0
Diffstat (limited to 'python/pyyaml/examples/pygments-lexer')
-rw-r--r--python/pyyaml/examples/pygments-lexer/example.yaml302
-rw-r--r--python/pyyaml/examples/pygments-lexer/yaml.py431
2 files changed, 733 insertions, 0 deletions
diff --git a/python/pyyaml/examples/pygments-lexer/example.yaml b/python/pyyaml/examples/pygments-lexer/example.yaml
new file mode 100644
index 000000000..9c0ed9d08
--- /dev/null
+++ b/python/pyyaml/examples/pygments-lexer/example.yaml
@@ -0,0 +1,302 @@
+
+#
+# Examples from the Preview section of the YAML specification
+# (http://yaml.org/spec/1.2/#Preview)
+#
+
+# Sequence of scalars
+---
+- Mark McGwire
+- Sammy Sosa
+- Ken Griffey
+
+# Mapping scalars to scalars
+---
+hr: 65 # Home runs
+avg: 0.278 # Batting average
+rbi: 147 # Runs Batted In
+
+# Mapping scalars to sequences
+---
+american:
+ - Boston Red Sox
+ - Detroit Tigers
+ - New York Yankees
+national:
+ - New York Mets
+ - Chicago Cubs
+ - Atlanta Braves
+
+# Sequence of mappings
+---
+-
+ name: Mark McGwire
+ hr: 65
+ avg: 0.278
+-
+ name: Sammy Sosa
+ hr: 63
+ avg: 0.288
+
+# Sequence of sequences
+---
+- [name , hr, avg ]
+- [Mark McGwire, 65, 0.278]
+- [Sammy Sosa , 63, 0.288]
+
+# Mapping of mappings
+---
+Mark McGwire: {hr: 65, avg: 0.278}
+Sammy Sosa: {
+ hr: 63,
+ avg: 0.288
+ }
+
+# Two documents in a stream
+--- # Ranking of 1998 home runs
+- Mark McGwire
+- Sammy Sosa
+- Ken Griffey
+--- # Team ranking
+- Chicago Cubs
+- St Louis Cardinals
+
+# Documents with the end indicator
+---
+time: 20:03:20
+player: Sammy Sosa
+action: strike (miss)
+...
+---
+time: 20:03:47
+player: Sammy Sosa
+action: grand slam
+...
+
+# Comments
+---
+hr: # 1998 hr ranking
+ - Mark McGwire
+ - Sammy Sosa
+rbi:
+ # 1998 rbi ranking
+ - Sammy Sosa
+ - Ken Griffey
+
+# Anchors and aliases
+---
+hr:
+ - Mark McGwire
+ # Following node labeled SS
+ - &SS Sammy Sosa
+rbi:
+ - *SS # Subsequent occurrence
+ - Ken Griffey
+
+# Mapping between sequences
+---
+? - Detroit Tigers
+ - Chicago cubs
+:
+ - 2001-07-23
+? [ New York Yankees,
+ Atlanta Braves ]
+: [ 2001-07-02, 2001-08-12,
+ 2001-08-14 ]
+
+# Inline nested mapping
+---
+# products purchased
+- item : Super Hoop
+ quantity: 1
+- item : Basketball
+ quantity: 4
+- item : Big Shoes
+ quantity: 1
+
+# Literal scalars
+--- | # ASCII art
+ \//||\/||
+ // || ||__
+
+# Folded scalars
+--- >
+ Mark McGwire's
+ year was crippled
+ by a knee injury.
+
+# Preserved indented block in a folded scalar
+---
+>
+ Sammy Sosa completed another
+ fine season with great stats.
+
+ 63 Home Runs
+ 0.288 Batting Average
+
+ What a year!
+
+# Indentation determines scope
+---
+name: Mark McGwire
+accomplishment: >
+ Mark set a major league
+ home run record in 1998.
+stats: |
+ 65 Home Runs
+ 0.278 Batting Average
+
+# Quoted scalars
+---
+unicode: "Sosa did fine.\u263A"
+control: "\b1998\t1999\t2000\n"
+hex esc: "\x0d\x0a is \r\n"
+single: '"Howdy!" he cried.'
+quoted: ' # not a ''comment''.'
+tie-fighter: '|\-*-/|'
+
+# Multi-line flow scalars
+---
+plain:
+ This unquoted scalar
+ spans many lines.
+quoted: "So does this
+ quoted scalar.\n"
+
+# Integers
+---
+canonical: 12345
+decimal: +12_345
+sexagesimal: 3:25:45
+octal: 014
+hexadecimal: 0xC
+
+# Floating point
+---
+canonical: 1.23015e+3
+exponential: 12.3015e+02
+sexagesimal: 20:30.15
+fixed: 1_230.15
+negative infinity: -.inf
+not a number: .NaN
+
+# Miscellaneous
+---
+null: ~
+true: boolean
+false: boolean
+string: '12345'
+
+# Timestamps
+---
+canonical: 2001-12-15T02:59:43.1Z
+iso8601: 2001-12-14t21:59:43.10-05:00
+spaced: 2001-12-14 21:59:43.10 -5
+date: 2002-12-14
+
+# Various explicit tags
+---
+not-date: !!str 2002-04-28
+picture: !!binary |
+ R0lGODlhDAAMAIQAAP//9/X
+ 17unp5WZmZgAAAOfn515eXv
+ Pz7Y6OjuDg4J+fn5OTk6enp
+ 56enmleECcgggoBADs=
+application specific tag: !something |
+ The semantics of the tag
+ above may be different for
+ different documents.
+
+# Global tags
+%TAG ! tag:clarkevans.com,2002:
+--- !shape
+ # Use the ! handle for presenting
+ # tag:clarkevans.com,2002:circle
+- !circle
+ center: &ORIGIN {x: 73, y: 129}
+ radius: 7
+- !line
+ start: *ORIGIN
+ finish: { x: 89, y: 102 }
+- !label
+ start: *ORIGIN
+ color: 0xFFEEBB
+ text: Pretty vector drawing.
+
+# Unordered sets
+--- !!set
+# sets are represented as a
+# mapping where each key is
+# associated with the empty string
+? Mark McGwire
+? Sammy Sosa
+? Ken Griff
+
+# Ordered mappings
+--- !!omap
+# ordered maps are represented as
+# a sequence of mappings, with
+# each mapping having one key
+- Mark McGwire: 65
+- Sammy Sosa: 63
+- Ken Griffy: 58
+
+# Full length example
+--- !<tag:clarkevans.com,2002:invoice>
+invoice: 34843
+date : 2001-01-23
+bill-to: &id001
+ given : Chris
+ family : Dumars
+ address:
+ lines: |
+ 458 Walkman Dr.
+ Suite #292
+ city : Royal Oak
+ state : MI
+ postal : 48046
+ship-to: *id001
+product:
+ - sku : BL394D
+ quantity : 4
+ description : Basketball
+ price : 450.00
+ - sku : BL4438H
+ quantity : 1
+ description : Super Hoop
+ price : 2392.00
+tax : 251.42
+total: 4443.52
+comments:
+ Late afternoon is best.
+ Backup contact is Nancy
+ Billsmer @ 338-4338.
+
+# Another full-length example
+---
+Time: 2001-11-23 15:01:42 -5
+User: ed
+Warning:
+ This is an error message
+ for the log file
+---
+Time: 2001-11-23 15:02:31 -5
+User: ed
+Warning:
+ A slightly different error
+ message.
+---
+Date: 2001-11-23 15:03:17 -5
+User: ed
+Fatal:
+ Unknown variable "bar"
+Stack:
+ - file: TopClass.py
+ line: 23
+ code: |
+ x = MoreObject("345\n")
+ - file: MoreClass.py
+ line: 58
+ code: |-
+ foo = bar
+
diff --git a/python/pyyaml/examples/pygments-lexer/yaml.py b/python/pyyaml/examples/pygments-lexer/yaml.py
new file mode 100644
index 000000000..1ce9dac9e
--- /dev/null
+++ b/python/pyyaml/examples/pygments-lexer/yaml.py
@@ -0,0 +1,431 @@
+
+"""
+yaml.py
+
+Lexer for YAML, a human-friendly data serialization language
+(http://yaml.org/).
+
+Written by Kirill Simonov <xi@resolvent.net>.
+
+License: Whatever suitable for inclusion into the Pygments package.
+"""
+
+from pygments.lexer import \
+ ExtendedRegexLexer, LexerContext, include, bygroups
+from pygments.token import \
+ Text, Comment, Punctuation, Name, Literal
+
+__all__ = ['YAMLLexer']
+
+
+class YAMLLexerContext(LexerContext):
+ """Indentation context for the YAML lexer."""
+
+ def __init__(self, *args, **kwds):
+ super(YAMLLexerContext, self).__init__(*args, **kwds)
+ self.indent_stack = []
+ self.indent = -1
+ self.next_indent = 0
+ self.block_scalar_indent = None
+
+
+def something(TokenClass):
+ """Do not produce empty tokens."""
+ def callback(lexer, match, context):
+ text = match.group()
+ if not text:
+ return
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+def reset_indent(TokenClass):
+ """Reset the indentation levels."""
+ def callback(lexer, match, context):
+ text = match.group()
+ context.indent_stack = []
+ context.indent = -1
+ context.next_indent = 0
+ context.block_scalar_indent = None
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+def save_indent(TokenClass, start=False):
+ """Save a possible indentation level."""
+ def callback(lexer, match, context):
+ text = match.group()
+ extra = ''
+ if start:
+ context.next_indent = len(text)
+ if context.next_indent < context.indent:
+ while context.next_indent < context.indent:
+ context.indent = context.indent_stack.pop()
+ if context.next_indent > context.indent:
+ extra = text[context.indent:]
+ text = text[:context.indent]
+ else:
+ context.next_indent += len(text)
+ if text:
+ yield match.start(), TokenClass, text
+ if extra:
+ yield match.start()+len(text), TokenClass.Error, extra
+ context.pos = match.end()
+ return callback
+
+def set_indent(TokenClass, implicit=False):
+ """Set the previously saved indentation level."""
+ def callback(lexer, match, context):
+ text = match.group()
+ if context.indent < context.next_indent:
+ context.indent_stack.append(context.indent)
+ context.indent = context.next_indent
+ if not implicit:
+ context.next_indent += len(text)
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+def set_block_scalar_indent(TokenClass):
+ """Set an explicit indentation level for a block scalar."""
+ def callback(lexer, match, context):
+ text = match.group()
+ context.block_scalar_indent = None
+ if not text:
+ return
+ increment = match.group(1)
+ if increment:
+ current_indent = max(context.indent, 0)
+ increment = int(increment)
+ context.block_scalar_indent = current_indent + increment
+ if text:
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+def parse_block_scalar_empty_line(IndentTokenClass, ContentTokenClass):
+ """Process an empty line in a block scalar."""
+ def callback(lexer, match, context):
+ text = match.group()
+ if (context.block_scalar_indent is None or
+ len(text) <= context.block_scalar_indent):
+ if text:
+ yield match.start(), IndentTokenClass, text
+ else:
+ indentation = text[:context.block_scalar_indent]
+ content = text[context.block_scalar_indent:]
+ yield match.start(), IndentTokenClass, indentation
+ yield (match.start()+context.block_scalar_indent,
+ ContentTokenClass, content)
+ context.pos = match.end()
+ return callback
+
+def parse_block_scalar_indent(TokenClass):
+ """Process indentation spaces in a block scalar."""
+ def callback(lexer, match, context):
+ text = match.group()
+ if context.block_scalar_indent is None:
+ if len(text) <= max(context.indent, 0):
+ context.stack.pop()
+ context.stack.pop()
+ return
+ context.block_scalar_indent = len(text)
+ else:
+ if len(text) < context.block_scalar_indent:
+ context.stack.pop()
+ context.stack.pop()
+ return
+ if text:
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+def parse_plain_scalar_indent(TokenClass):
+ """Process indentation spaces in a plain scalar."""
+ def callback(lexer, match, context):
+ text = match.group()
+ if len(text) <= context.indent:
+ context.stack.pop()
+ context.stack.pop()
+ return
+ if text:
+ yield match.start(), TokenClass, text
+ context.pos = match.end()
+ return callback
+
+
+class YAMLLexer(ExtendedRegexLexer):
+ """Lexer for the YAML language."""
+
+ name = 'YAML'
+ aliases = ['yaml']
+ filenames = ['*.yaml', '*.yml']
+ mimetypes = ['text/x-yaml']
+
+ tokens = {
+
+ # the root rules
+ 'root': [
+ # ignored whitespaces
+ (r'[ ]+(?=#|$)', Text.Blank),
+ # line breaks
+ (r'\n+', Text.Break),
+ # a comment
+ (r'#[^\n]*', Comment.Single),
+ # the '%YAML' directive
+ (r'^%YAML(?=[ ]|$)', reset_indent(Name.Directive),
+ 'yaml-directive'),
+ # the %TAG directive
+ (r'^%TAG(?=[ ]|$)', reset_indent(Name.Directive),
+ 'tag-directive'),
+ # document start and document end indicators
+ (r'^(?:---|\.\.\.)(?=[ ]|$)',
+ reset_indent(Punctuation.Document), 'block-line'),
+ # indentation spaces
+ (r'[ ]*(?![ \t\n\r\f\v]|$)',
+ save_indent(Text.Indent, start=True),
+ ('block-line', 'indentation')),
+ ],
+
+ # trailing whitespaces after directives or a block scalar indicator
+ 'ignored-line': [
+ # ignored whitespaces
+ (r'[ ]+(?=#|$)', Text.Blank),
+ # a comment
+ (r'#[^\n]*', Comment.Single),
+ # line break
+ (r'\n', Text.Break, '#pop:2'),
+ ],
+
+ # the %YAML directive
+ 'yaml-directive': [
+ # the version number
+ (r'([ ]+)([0-9]+\.[0-9]+)',
+ bygroups(Text.Blank, Literal.Version), 'ignored-line'),
+ ],
+
+ # the %YAG directive
+ 'tag-directive': [
+ # a tag handle and the corresponding prefix
+ (r'([ ]+)(!|![0-9A-Za-z_-]*!)'
+ r'([ ]+)(!|!?[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)',
+ bygroups(Text.Blank, Name.Type, Text.Blank, Name.Type),
+ 'ignored-line'),
+ ],
+
+ # block scalar indicators and indentation spaces
+ 'indentation': [
+ # trailing whitespaces are ignored
+ (r'[ ]*$', something(Text.Blank), '#pop:2'),
+ # whitespaces preceeding block collection indicators
+ (r'[ ]+(?=[?:-](?:[ ]|$))', save_indent(Text.Indent)),
+ # block collection indicators
+ (r'[?:-](?=[ ]|$)', set_indent(Punctuation.Indicator)),
+ # the beginning a block line
+ (r'[ ]*', save_indent(Text.Indent), '#pop'),
+ ],
+
+ # an indented line in the block context
+ 'block-line': [
+ # the line end
+ (r'[ ]*(?=#|$)', something(Text.Blank), '#pop'),
+ # whitespaces separating tokens
+ (r'[ ]+', Text.Blank),
+ # tags, anchors and aliases,
+ include('descriptors'),
+ # block collections and scalars
+ include('block-nodes'),
+ # flow collections and quoted scalars
+ include('flow-nodes'),
+ # a plain scalar
+ (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`-]|[?:-][^ \t\n\r\f\v])',
+ something(Literal.Scalar.Plain),
+ 'plain-scalar-in-block-context'),
+ ],
+
+ # tags, anchors, aliases
+ 'descriptors' : [
+ # a full-form tag
+ (r'!<[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+>', Name.Type),
+ # a tag in the form '!', '!suffix' or '!handle!suffix'
+ (r'!(?:[0-9A-Za-z_-]+)?'
+ r'(?:![0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)?', Name.Type),
+ # an anchor
+ (r'&[0-9A-Za-z_-]+', Name.Anchor),
+ # an alias
+ (r'\*[0-9A-Za-z_-]+', Name.Alias),
+ ],
+
+ # block collections and scalars
+ 'block-nodes': [
+ # implicit key
+ (r':(?=[ ]|$)', set_indent(Punctuation.Indicator, implicit=True)),
+ # literal and folded scalars
+ (r'[|>]', Punctuation.Indicator,
+ ('block-scalar-content', 'block-scalar-header')),
+ ],
+
+ # flow collections and quoted scalars
+ 'flow-nodes': [
+ # a flow sequence
+ (r'\[', Punctuation.Indicator, 'flow-sequence'),
+ # a flow mapping
+ (r'\{', Punctuation.Indicator, 'flow-mapping'),
+ # a single-quoted scalar
+ (r'\'', Literal.Scalar.Flow.Quote, 'single-quoted-scalar'),
+ # a double-quoted scalar
+ (r'\"', Literal.Scalar.Flow.Quote, 'double-quoted-scalar'),
+ ],
+
+ # the content of a flow collection
+ 'flow-collection': [
+ # whitespaces
+ (r'[ ]+', Text.Blank),
+ # line breaks
+ (r'\n+', Text.Break),
+ # a comment
+ (r'#[^\n]*', Comment.Single),
+ # simple indicators
+ (r'[?:,]', Punctuation.Indicator),
+ # tags, anchors and aliases
+ include('descriptors'),
+ # nested collections and quoted scalars
+ include('flow-nodes'),
+ # a plain scalar
+ (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`])',
+ something(Literal.Scalar.Plain),
+ 'plain-scalar-in-flow-context'),
+ ],
+
+ # a flow sequence indicated by '[' and ']'
+ 'flow-sequence': [
+ # include flow collection rules
+ include('flow-collection'),
+ # the closing indicator
+ (r'\]', Punctuation.Indicator, '#pop'),
+ ],
+
+ # a flow mapping indicated by '{' and '}'
+ 'flow-mapping': [
+ # include flow collection rules
+ include('flow-collection'),
+ # the closing indicator
+ (r'\}', Punctuation.Indicator, '#pop'),
+ ],
+
+ # block scalar lines
+ 'block-scalar-content': [
+ # line break
+ (r'\n', Text.Break),
+ # empty line
+ (r'^[ ]+$',
+ parse_block_scalar_empty_line(Text.Indent,
+ Literal.Scalar.Block)),
+ # indentation spaces (we may leave the state here)
+ (r'^[ ]*', parse_block_scalar_indent(Text.Indent)),
+ # line content
+ (r'[^\n\r\f\v]+', Literal.Scalar.Block),
+ ],
+
+ # the content of a literal or folded scalar
+ 'block-scalar-header': [
+ # indentation indicator followed by chomping flag
+ (r'([1-9])?[+-]?(?=[ ]|$)',
+ set_block_scalar_indent(Punctuation.Indicator),
+ 'ignored-line'),
+ # chomping flag followed by indentation indicator
+ (r'[+-]?([1-9])?(?=[ ]|$)',
+ set_block_scalar_indent(Punctuation.Indicator),
+ 'ignored-line'),
+ ],
+
+ # ignored and regular whitespaces in quoted scalars
+ 'quoted-scalar-whitespaces': [
+ # leading and trailing whitespaces are ignored
+ (r'^[ ]+|[ ]+$', Text.Blank),
+ # line breaks are ignored
+ (r'\n+', Text.Break),
+ # other whitespaces are a part of the value
+ (r'[ ]+', Literal.Scalar.Flow),
+ ],
+
+ # single-quoted scalars
+ 'single-quoted-scalar': [
+ # include whitespace and line break rules
+ include('quoted-scalar-whitespaces'),
+ # escaping of the quote character
+ (r'\'\'', Literal.Scalar.Flow.Escape),
+ # regular non-whitespace characters
+ (r'[^ \t\n\r\f\v\']+', Literal.Scalar.Flow),
+ # the closing quote
+ (r'\'', Literal.Scalar.Flow.Quote, '#pop'),
+ ],
+
+ # double-quoted scalars
+ 'double-quoted-scalar': [
+ # include whitespace and line break rules
+ include('quoted-scalar-whitespaces'),
+ # escaping of special characters
+ (r'\\[0abt\tn\nvfre "\\N_LP]', Literal.Scalar.Flow.Escape),
+ # escape codes
+ (r'\\(?:x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})',
+ Literal.Scalar.Flow.Escape),
+ # regular non-whitespace characters
+ (r'[^ \t\n\r\f\v\"\\]+', Literal.Scalar.Flow),
+ # the closing quote
+ (r'"', Literal.Scalar.Flow.Quote, '#pop'),
+ ],
+
+ # the beginning of a new line while scanning a plain scalar
+ 'plain-scalar-in-block-context-new-line': [
+ # empty lines
+ (r'^[ ]+$', Text.Blank),
+ # line breaks
+ (r'\n+', Text.Break),
+ # document start and document end indicators
+ (r'^(?=---|\.\.\.)', something(Punctuation.Document), '#pop:3'),
+ # indentation spaces (we may leave the block line state here)
+ (r'^[ ]*', parse_plain_scalar_indent(Text.Indent), '#pop'),
+ ],
+
+ # a plain scalar in the block context
+ 'plain-scalar-in-block-context': [
+ # the scalar ends with the ':' indicator
+ (r'[ ]*(?=:[ ]|:$)', something(Text.Blank), '#pop'),
+ # the scalar ends with whitespaces followed by a comment
+ (r'[ ]+(?=#)', Text.Blank, '#pop'),
+ # trailing whitespaces are ignored
+ (r'[ ]+$', Text.Blank),
+ # line breaks are ignored
+ (r'\n+', Text.Break, 'plain-scalar-in-block-context-new-line'),
+ # other whitespaces are a part of the value
+ (r'[ ]+', Literal.Scalar.Plain),
+ # regular non-whitespace characters
+ (r'(?::(?![ \t\n\r\f\v])|[^ \t\n\r\f\v:])+',
+ Literal.Scalar.Plain),
+ ],
+
+ # a plain scalar is the flow context
+ 'plain-scalar-in-flow-context': [
+ # the scalar ends with an indicator character
+ (r'[ ]*(?=[,:?\[\]{}])', something(Text.Blank), '#pop'),
+ # the scalar ends with a comment
+ (r'[ ]+(?=#)', Text.Blank, '#pop'),
+ # leading and trailing whitespaces are ignored
+ (r'^[ ]+|[ ]+$', Text.Blank),
+ # line breaks are ignored
+ (r'\n+', Text.Break),
+ # other whitespaces are a part of the value
+ (r'[ ]+', Literal.Scalar.Plain),
+ # regular non-whitespace characters
+ (r'[^ \t\n\r\f\v,:?\[\]{}]+', Literal.Scalar.Plain),
+ ],
+
+ }
+
+ def get_tokens_unprocessed(self, text=None, context=None):
+ if context is None:
+ context = YAMLLexerContext(text, 0)
+ return super(YAMLLexer, self).get_tokens_unprocessed(text, context)
+
+