Newer
Older
Silas S. Brown
committed
#!/usr/bin/env python
# (compatible with both Python 2.7 and Python 3)
"Annotator Generator v3.161 (c) 2012-21 Silas S. Brown"
Silas S. Brown
committed
# See http://ssb22.user.srcf.net/adjuster/annogen.html
# Licensed 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.
# If you want to compare this code to old versions, the old
# versions are being kept in the E-GuideDog SVN repository on
# http://svn.code.sf.net/p/e-guidedog/code/ssb22/adjuster
# and on GitHub at https://github.com/ssb22/adjuster
# and on GitLab at https://gitlab.com/ssb22/adjuster
# and on BitBucket https://bitbucket.org/ssb22/adjuster
# and at https://gitlab.developers.cam.ac.uk/ssb22/adjuster
# and in China: https://gitee.com/ssb22/adjuster
Silas S. Brown
committed
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
# although some early ones are missing.
from optparse import OptionParser
parser = OptionParser()
import sys,os,os.path,tempfile,time,re,subprocess,unicodedata
try: from subprocess import getoutput
except: from commands import getoutput
if not "mac" in sys.platform and not "darwin" in sys.platform and ("win" in sys.platform or "mingw32" in sys.platform): exe=".exe" # Windows, Cygwin, etc
else: exe=""
# =========== INPUT OPTIONS ==============
parser.add_option("--infile",
help="Filename of a text file (or a compressed .gz, .bz2 or .xz file or URL) to read the input examples from. If this is not specified, standard input is used.")
parser.add_option("--incode",default="utf-8",
help="Character encoding of the input file (default %default)")
parser.add_option("--mstart",
dest="markupStart",
default="<ruby><rb>",
help="The string that starts a piece of text with annotation markup in the input examples; default %default")
parser.add_option("--mmid",
dest="markupMid",
default="</rb><rt>",
help="The string that occurs in the middle of a piece of markup in the input examples, with the word on its left and the added markup on its right (or the other way around if mreverse is set); default %default")
parser.add_option("--mend",
dest="markupEnd",
default="</rt></ruby>",
help="The string that ends a piece of annotation markup in the input examples; default %default")
parser.add_option("-r","--mreverse",
action="store_true",default=False,
help="Specifies that the annotation markup is reversed, so the text BEFORE mmid is the annotation and the text AFTER it is the base text")
def cancelOpt(opt,act="store_false",dst=None):
if not dst: dst=opt.replace("-","_")
parser.add_option("--no-"+opt,action=act,dest=dst,help="Cancels any earlier --"+opt+" option in Makefile variables etc")
cancelOpt("mreverse")
parser.add_option("--reference-sep",
help="Reference separator code used in the example input. If you want to keep example source references for each rule, you can label the input with 'references' (chapter and section numbers or whatever), and use this option to specify what keyword or other markup the input will use between each 'reference'. The name of the next reference will be whatever text immediately follows this string. Note that the reference separator, and the reference name that follows it, should not be part of the text itself and should therefore not be part of any annotation markup. If this option is not set then references will not be tracked.")
parser.add_option("--ref-name-end",default=" ",
help="Sets what the input uses to END a reference name. The default is a single space, so that the first space after the reference-sep string will end the reference name.")
parser.add_option("--ref-pri",
help="Name of a reference to be considered \"high priority\" for Yarowsky-like seed collocations (if these are in use). Normally the Yarowsky-like logic tries to identify a \"default\" annotation based on what is most common in the examples, with the exceptions indicated by collocations. If however a word is found in a high priority reference then the first annotation found in that reference will be considered the ideal \"default\" even if it's in a minority in the examples; everything else will be considered as an exception.")
parser.add_option("-s", "--spaces",
action="store_false",
dest="removeSpace",
default=True,
help="Set this if you are working with a language that uses whitespace in its non-markedup version (not fully tested). The default is to assume that there will not be any whitespace in the language, which is correct for Chinese and Japanese.")
cancelOpt("spaces","store_true","removeSpace")
parser.add_option("-c", "--capitalisation",
action="store_true",
default=False,
help="Don't try to normalise capitalisation in the input. Normally, to simplify the rules, the analyser will try to remove start-of-sentence capitals in annotations, so that the only remaining words with capital letters are the ones that are ALWAYS capitalised such as names. (That's not perfect: some words might always be capitalised just because they never occur mid-sentence in the examples.) If this option is used, the analyser will instead try to \"learn\" how to predict the capitalisation of ALL words (including start of sentence words) from their contexts.") # TODO: make the C program put the sentence capitals back
cancelOpt("capitalisation")
parser.add_option("-w", "--annot-whitespace",
action="store_true",
default=False,
help="Don't try to normalise the use of whitespace and hyphenation in the example annotations. Normally the analyser will try to do this, to reduce the risk of missing possible rules due to minor typographical variations.") # TODO: can this be extended to the point where the words 'try to' can be deleted ? see comments
cancelOpt("annot-whitespace")
parser.add_option("--keep-whitespace",
help="Comma-separated list of words (without annotation markup) for which whitespace and hyphenation should always be kept even without the --annot-whitespace option. Use when you know the variation is legitimate. This option expects words to be encoded using the system locale (UTF-8 if it cannot be detected).")
parser.add_option("--normalised-file",
help="Filename of an optional text file (or compressed .gz, .bz2 or .xz file) to write a copy of the normalised input for diagnostic purposes. If this is set to the same as --infile then it will be assumed the input file has already been normalised (use with care).")
parser.add_option("--normalise-only",
action="store_true",
default=False,
help="Exit after normalising the input")
cancelOpt("normalise-only")
parser.add_option("--post-normalise",
help="Filename of an optional Python module defining a dictionary called 'table' mapping integers to integers for arbitrary single-character normalisation on the Unicode BMP. This is meant for reducing the size of generated Android apps, and is applied in post-processing (does not affect rules generation itself). For example this can be used to merge the recognition of Full, Simplified and Variant forms of the same Chinese character in cases where this can be done without ambiguity, if it is acceptable for the generated annotator to recognise mixed-script words should they occur.")
parser.add_option("--glossfile",
help="Filename of an optional text file (or compressed .gz, .bz2 or .xz file or URL) to read auxiliary \"gloss\" information. Each line of this should be of the form: word (tab) annotation (tab) gloss. Extra tabs in the gloss will be converted to newlines (useful if you want to quote multiple dictionaries). When the compiled annotator generates ruby markup, it will add the gloss string as a popup title whenever that word is used with that annotation (before any reannotator option is applied). The annotation field may be left blank to indicate that the gloss will appear for all other annotations of that word. The entries in glossfile do NOT affect the annotation process itself, so it's not necessary to completely debug glossfile's word segmentation etc.")
parser.add_option("-C", "--gloss-closure",
action="store_true",
default=False,
help="If any Chinese, Japanese or Korean word is missing from glossfile, search its closure of variant characters also. This option requires the cjklib package.") # TODO: option to put variant closures into the annotator itself? (generate new rules if not already exist + closure the 'near' tests) but that could unnecessarily increase the annotator size (with --data-driven the increase could be significant unless we implement shared-substringVariants optimisations, and even then it's unclear how this would interact with the space-saving of common-prefix multibyte sequences), + it might not be correct in all cases, e.g. U+91CC in jianti SHOULDN'T be translated to U+88E1/U+88CF in fanti if it's part of a name, although recognising a 'messed-up' name with that substitution might be acceptable. Anyway, using these closures to fill in a missing gloss should be tolerable.
cancelOpt("gloss-closure")
parser.add_option("--glossmiss",
help="Name of an optional file to which to write information about words recognised by the annotator that are missing in glossfile (along with frequency counts and references, if available)") # (default sorted alphabetically, but you can pipe through sort -rn to get most freq 1st)
parser.add_option("--glossmiss-hide",
help="Comma-separated list of references to hide from the glossmiss file (does not affect the glossmiss-omit option)")
parser.add_option("--glossmiss-match",
help="If supplied, any references not matching this regular expression will be hidden from the glossmiss file (does not affect the glossmiss-omit option)")
parser.add_option("-M","--glossmiss-omit",
action="store_true",
default=False,
help="Omit rules containing any word not mentioned in glossfile. Might be useful if you want to train on a text that uses proprietary terms and don't want to accidentally 'leak' those terms (assuming they're not accidentally included in glossfile also). Words may also be listed in glossfile with an empty gloss field to indicate that no gloss is available but rules using this word needn't be omitted.")
cancelOpt("glossmiss-omit")
parser.add_option("--words-omit",
help="File (or compressed .gz, .bz2 or .xz file or URL) containing words (one per line, without markup) to omit from the annotator. Use this to make an annotator smaller if for example if you're working from a rules file that contains long lists of place names you don't need this particular annotator to recognise but you still want to keep them as rules for other annotators, but be careful because any word on such a list gets omitted even if it also has other meanings (some place names are also normal words).")
parser.add_option("--manualrules",
help="Filename of an optional text file (or compressed .gz, .bz2 or .xz file or URL) to read extra, manually-written rules. Each line of this should be a marked-up phrase (in the input format) which is to be unconditionally added as a rule. Use this sparingly, because these rules are not taken into account when generating the others and they will be applied regardless of context (although a manual rule might fail to activate if the annotator is part-way through processing a different rule); try checking messages from --diagnose-manual.") # (or if there's a longer automatic match)
# =========== OUTPUT OPTIONS ==============
parser.add_option("--rulesFile",help="Filename of an optional auxiliary binary file to hold the accumulated rules. Adding .gz, .bz2 or .xz for compression is acceptable. If this is set then the rules will be written to it (in binary format) as well as to the output. Additionally, if the file already exists then rules will be read from it and incrementally updated. This might be useful if you have made some small additions to the examples and would like these to be incorporated without a complete re-run. It might not work as well as a re-run but it should be faster. If using a rulesFile then you must keep the same input (you may make small additions etc, but it won't work properly if you delete many examples or change the format between runs) and you must keep the same ybytes-related options if any.") # You may however change whether or not a --single-words / --max-words option applies to the new examples (but hopefully shouldn't have to)
parser.add_option("-n","--no-input",
action="store_true",default=False,
help="Don't process new input, just use the rules that were previously stored in rulesFile. This can be used to increase speed if the only changes made are to the output options. You should still specify the input formatting options (which should not change), and any glossfile or manualrules options (which may change). For the glossmiss and summary options to work correctly, unchanged input should be provided.")
cancelOpt("no-input")
parser.add_option("--c-filename",default="",help="Where to write the C, C#, Python, Javascript, Go or Dart program. Defaults to standard output, or annotator.c in the system temporary directory if standard output seems to be the terminal (the program might be large, especially if Yarowsky-like indicators are not used, so it's best not to use a server home directory where you might have limited quota). If MPI is in use then the default will always be standard output.") # because the main program might not be running on the launch node
parser.add_option("--c-compiler",default="cc -o annotator"+exe,help="The C compiler to run if generating C and standard output is not connected to a pipe. The default is to use the \"cc\" command which usually redirects to your \"normal\" compiler. You can add options (remembering to enclose this whole parameter in quotes if it contains spaces), but if the C program is large then adding optimisation options may make the compile take a LONG time. If standard output is connected to a pipe, then this option is ignored because the C code will simply be written to the pipe. You can also set this option to an empty string to skip compilation. Default: %default")
# If compiling an experimental annotator quickly (and don't want to use --data-driven for some reason), then you might try tcc as it compiles fast. If tcc is not available on your system then clang might compile faster than gcc.
# (BUT tcc can have problems on Raspberry Pi see http://www.raspberrypi.org/phpBB3/viewtopic.php?t=30036&p=263213; can be best to cross-compile, e.g. from a Mac use https://github.com/UnhandledException/ARMx/wiki/Sourcery-G---Lite-for-ARM-GNU-Linux-(2009q3-67)-for-Mac-OS-X and arm-none-linux-gnueabi-gcc)
# In large rulesets with --max-or-length=0 and --nested-switch, gcc takes time and gcc -Os can take a LOT longer, and CINT, Ch and picoc run out of memory. Without these options the overhead of gcc's -Os isn't so bad (and does save some room).
# clang with --max-or-length=100 and --nested-switch=0 is not slowed much by -Os (slowed considerably by -O3). -Os and -Oz gave same size in my tests.
# on 64-bit distros -m32 won't always work and won't necessarily give a smaller program
parser.add_option("--max-or-length",default=100,help="The maximum number of items allowed in an OR-expression in non table-driven code (used when ybytes is in effect). When an OR-expression becomes larger than this limit, it will be made into a function. 0 means unlimited, which works for tcc and gcc; many other compilers have limits. Default: %default")
parser.add_option("--nested-if",
action="store_true",default=False,
help="Allow C/C#/Java/Go if() blocks (but not switch() constructs) to be nested to unlimited depth. This probably increases the workload of the compiler's optimiser when reducing size, but may help when optimising for speed.")
cancelOpt("nested-if")
parser.add_option("--nested-switch",default=0,
help="Allow C/C#/Java/Go switch() constructs to be nested to about this depth. Default 0 tries to avoid nesting, as it slows down most C compilers for small savings in executable size. Setting 1 nests 1 level deeper which can occasionally help get around memory problems with Java compilers. -1 means nest to unlimited depth, which is not recommended. Setting this to anything other than 0 implies --nested-if also.") # tcc is still fast (although that doesn't generate the smallest executables anyway)
parser.add_option("--outcode",default="utf-8",
help="Character encoding to use in the generated parser and rules summary (default %default, must be ASCII-compatible i.e. not utf-16)")
parser.add_option("-S", "--summary-only",
action="store_true",default=False,
help="Don't generate a parser, just write the rules summary to standard output")
cancelOpt("summary-only")
parser.add_option("-N","--no-summary",
action="store_true",default=False,
help="Don't add a large rules-summary comment at the end of the parser code")
cancelOpt("no-summary")
parser.add_option("-O", "--summary-omit",
help="Filename of a text file (or a compressed .gz, .bz2 or .xz file or URL) specifying what should be omitted from the rules summary. Each line should be a word or phrase, a tab, and its annotation (without the mstart/mmid/mend markup). If any rule in the summary exactly matches any of the lines in this text file, then that rule will be omitted from the summary (but still included in the parser). Use for example to take out of the summary any entries that correspond to things you already have in your dictionary, so you can see what's new.")
parser.add_option("--maxrefs",default=3,
help="The maximum number of example references to record in each summary line, if references are being recorded (0 means unlimited). Default is %default.")
parser.add_option("-R","--norefs",
action="store_true",default=False,
help="Don't write references in the rules summary (or the glossmiss file). Use this if you need to specify reference-sep and ref-name-end for the ref-pri option but you don't actually want references in the summary (which speeds up summary generation slightly). This option is automatically turned on if --no-input is specified.") # the speed difference is not so great as of v0.593, but needed anyway if --no-input is set
cancelOpt("norefs")
parser.add_option("-E","--newlines-reset",
action="store_false",
dest="ignoreNewlines",
default=True,
help="Have the annotator reset its state on every newline byte. By default newlines do not affect state such as whether a space is required before the next word, so that if the annotator is used with Web Adjuster's htmlText option (which defaults to using newline separators) the spacing should be handled sensibly when there is HTML markup in mid-sentence.")
cancelOpt("newlines-reset","store_true","ignoreNewlines")
parser.add_option("-z","--compress",
action="store_true",default=False,
help="Compress annotation strings in the C code. This compression is designed for fast on-the-fly decoding, so it saves only a limited amount of space (typically 10-20%) but might help if RAM is short; see also --data-driven.")
cancelOpt("compress")
parser.add_option("-D","--data-driven",
action="store_true",default=False,
help="Generate a program that works by interpreting embedded data tables for comparisons, instead of writing these as code. This can take some load off the compiler (so try it if you get errors like clang's \"section too large\"), as well as compiling faster and reducing the resulting binary's RAM size (by 35-40% is typical), at the expense of a small reduction in execution speed. Javascript, Python and Dart output is always data-driven anyway.") # If the resulting binary is compressed (e.g. in an APK), its compressed size will likely not change much (same information content), so I'm specifically saying "RAM size" i.e. when decompressed
Loading
Loading full blame...