annogen.py

#!/usr/bin/env python

program_name = "Annotator Generator v0.626 (c) 2012-17 Silas S. Brown"

# See http://people.ds.cam.ac.uk/ssb22/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
# although some early ones are missing.

from optparse import OptionParser
parser = OptionParser()
import sys,os,os.path,tempfile,time,re
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 or .bz2 file) 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("--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")

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.  In languages without spaces, this override should normally be used only for one-character words; if used with longer words it might have unexpected effects on rule-overlap ambiguities.")

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.")

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

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
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("--glossfile",
                  help="Filename of an optional text file (or compressed .gz or .bz2 file) to read auxiliary \"gloss\" information.  Each line of this should be of the form: word (tab) annotation (tab) gloss.  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.  The annotation field may be left blank to indicate that the gloss will appear for any annotation 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("--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("--manualrules",
                  help="Filename of an optional text file (or compressed .gz or .bz2 file) 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 or .bz2 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("--no-input",
                  action="store_true",default=False,
                  help="Don't actually read the 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).")

parser.add_option("--c-filename",default="",help="Where to write the C 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 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 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, 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-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.") # 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")

parser.add_option("--no-summary",
                  action="store_true",default=False,
                  help="Don't add a large rules-summary comment at the end of the parser code")

parser.add_option("-O", "--summary-omit",
                  help="Filename of a text file (or a compressed .gz or .bz2 file) 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("--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

parser.add_option("--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.")

parser.add_option("--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 that might help if memory is short; see also --data-driven.")

parser.add_option("--ios",
                  help="Include Objective-C code for an iOS app that opens a web-browser component and annotates the text on every page it loads.  The initial page is specified by this option: it can be a URL, or a markup fragment starting with < to hard-code the contents of the page. Also provided is a custom URL scheme to annotate the local clipboard. You will need Xcode to compile the app (see the start of the generated C file for instructions); if it runs out of space, try using --data-driven")

parser.add_option("--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 and Python 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

parser.add_option("--zlib",
                  action="store_true",default=False,
                  help="Enable --data-driven and compress the embedded data table using zlib, and include code to call zlib to decompress it on load.  Useful if the runtime machine has the zlib library and you need to save disk space but not RAM (the decompressed table is stored separately in RAM, unlike --compress which, although giving less compression, at least works 'in place').  Once --zlib is in use, specifying --compress too will typically give an additional disk space saving of less than 1% (and a runtime RAM saving that's greater but more than offset by zlib's extraction RAM).") # and additional_compact_opcodes typically still helps no matter what the other options are

parser.add_option("--windows-clipboard",
                  action="store_true",default=False,
                  help="Include C code to read the clipboard on Windows or Windows Mobile and to write an annotated HTML file and launch a browser, instead of using the default cross-platform command-line C wrapper.  See the start of the generated C file for instructions on how to compile for Windows or Windows Mobile.")

parser.add_option("--c-sharp",
                  action="store_true",default=False,
                  help="Instead of generating C code, generate C# (not quite as efficient as the C code but close; might be useful for adding an annotator to a C# project; see comments at the start for usage)")

parser.add_option("--java",
                  help="Instead of generating C code, generate Java, and place the *.java files in the directory specified by this option, removing any existing *.java files.  See --android for example use.  The last part of the directory should be made up of the package name; a double slash (//) should separate the rest of the path from the package name, e.g. --java=/path/to/wherever//org/example/package and the main class will be called Annotator.")
parser.add_option("--android",
                  help="URL for an Android app to browse.  If this is set, code is generated for an Android app which starts a browser with that URL as the start page, and annotates the text on every page it loads.  A function to annotate the local clipboard is also provided.  You will need the Android SDK to compile the app; see comments in MainActivity.java for details.")
parser.add_option("--ndk",
                  help="Android NDK: make a C annotator and use ndk-build to compile it into an Android JNI library.  This is a more complex setup than a Java-based annotator, but it improves speed and size.  The --ndk option should be set to the name of the package that will use the library, and --android should be set to the initial URL.  See comments in the output file for details.")

parser.add_option("--javascript",
                  action="store_true",default=False,
                  help="Instead of generating C code, generate JavaScript.  This might be useful if you want to run an annotator on a device that has a JS interpreter but doesn't let you run native code.  The JS will be table-driven to make it load faster (and --no-summary will also be set).  See comments at the start for usage.") # but it's better to use the C version if you're in an environment where 'standard input' makes sense

parser.add_option("--python",
                  action="store_true",default=False,
                  help="Instead of generating C code, generate a Python module.  Similar to the Javascript option, this is for when you can't run native code, and it is table-driven for fast loading.")

parser.add_option("--golang",
                  help="Package name for a Go library to generate instead of C code.  See comments in the generated file for how to run this on AppEngine.")

parser.add_option("--reannotator",
                  help="Shell command through which to pipe each word of the original text to obtain new annotation for that word.  This might be useful as a quick way of generating a new annotator (e.g. for a different topolect) while keeping the information about word separation and/or glosses from the previous annotator, but it is limited to commands that don't need to look beyond the boundaries of each word.  If the command is prefixed by a # character, it will be given the word's existing annotation instead of its original text, and if prefixed by ## it will be given text#annotation.  The command should treat each line of its input independently, and both its input and its output should be in the encoding specified by --outcode.") # TODO: reannotatorCode instead? (see other 'reannotatorCode' TODOs)
# (Could just get the reannotator to post-process the 1st annotator's output, but that might be slower than generating an altered annotator with it)

#  =========== ANALYSIS OPTIONS ==============

parser.add_option("-o", "--allow-overlaps",
                  action="store_true",default=False,
                  help="Normally, the analyser avoids generating rules that could overlap with each other in a way that would leave the program not knowing which one to apply.  If a short rule would cause overlaps, the analyser will prefer to generate a longer rule that uses more context, and if even the entire phrase cannot be made into a rule without causing overlaps then the analyser will give up on trying to cover that phrase.  This option allows the analyser to generate rules that could overlap, as long as none of the overlaps would cause actual problems in the example phrases. Thus more of the examples can be covered, at the expense of a higher risk of ambiguity problems when applying the rules to other texts.  See also the -y option.")

parser.add_option("-P", "--primitive",
                  action="store_true",default=False,
                  help="Don't bother with any overlap or conflict checks at all, just make a rule for each word. The resulting parser is not likely to be useful, but the summary might be.")

parser.add_option("-y","--ybytes",default=0,
                  help="Look for candidate Yarowsky seed-collocations within this number of bytes of the end of a word.  If this is set then overlaps and rule conflicts will be allowed if the seed collocations can be used to distinguish between them.  Markup examples that are completely separate (e.g. sentences from different sources) must have at least this number of (non-whitespace) bytes between them.")
parser.add_option("--ybytes-max",default=0,
                  help="Extend the Yarowsky seed-collocation search to check over larger ranges up to this maximum.  If this is set then several ranges will be checked in an attempt to determine the best one for each word, but see also ymax-threshold.")
parser.add_option("--ymax-threshold",default=1,