# HG changeset patch
# User Alpar Juttner <alpar@cs.elte.hu>
# Date 1363624879 -3600
# Node ID 1c978b5bcc657cc3c0623b96d72f94cd60ae40a1
# Parent eb2f9d453070f2251c5c194610f0722d1670df31
Use doxygen's own bibtex support (#456)
diff -r eb2f9d453070 -r 1c978b5bcc65 doc/CMakeLists.txt
--- a/doc/CMakeLists.txt Sat Mar 16 14:11:32 2013 +0100
+++ b/doc/CMakeLists.txt Mon Mar 18 17:41:19 2013 +0100
@@ -51,7 +51,6 @@
COMMAND ${GHOSTSCRIPT_EXECUTABLE} ${GHOSTSCRIPT_OPTIONS} -r8 -sOutputFile=gen-images/nodeshape_3.png ${CMAKE_CURRENT_SOURCE_DIR}/images/nodeshape_3.eps
COMMAND ${GHOSTSCRIPT_EXECUTABLE} ${GHOSTSCRIPT_OPTIONS} -r8 -sOutputFile=gen-images/nodeshape_4.png ${CMAKE_CURRENT_SOURCE_DIR}/images/nodeshape_4.eps
COMMAND ${CMAKE_COMMAND} -E remove_directory html
- COMMAND ${PYTHON_EXECUTABLE} ${PROJECT_SOURCE_DIR}/scripts/bib2dox.py ${CMAKE_CURRENT_SOURCE_DIR}/references.bib >references.dox
COMMAND ${DOXYGEN_EXECUTABLE} Doxyfile
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
)
diff -r eb2f9d453070 -r 1c978b5bcc65 doc/Doxyfile.in
--- a/doc/Doxyfile.in Sat Mar 16 14:11:32 2013 +0100
+++ b/doc/Doxyfile.in Mon Mar 18 17:41:19 2013 +0100
@@ -77,6 +77,7 @@
SHOW_NAMESPACES = YES
FILE_VERSION_FILTER =
LAYOUT_FILE = "@abs_top_srcdir@/doc/DoxygenLayout.xml"
+CITE_BIB_FILES = "@abs_top_srcdir@/doc/references.bib"
#---------------------------------------------------------------------------
# configuration options related to warning and progress messages
#---------------------------------------------------------------------------
diff -r eb2f9d453070 -r 1c978b5bcc65 doc/groups.dox
--- a/doc/groups.dox Sat Mar 16 14:11:32 2013 +0100
+++ b/doc/groups.dox Mon Mar 18 17:41:19 2013 +0100
@@ -317,7 +317,7 @@
This group contains the common graph search algorithms, namely
\e breadth-first \e search (BFS) and \e depth-first \e search (DFS)
-\ref clrs01algorithms.
+\cite clrs01algorithms.
*/
/**
@@ -326,7 +326,7 @@
\brief Algorithms for finding shortest paths.
This group contains the algorithms for finding shortest paths in digraphs
-\ref clrs01algorithms.
+\cite clrs01algorithms.
- \ref Dijkstra algorithm for finding shortest paths from a source node
when all arc lengths are non-negative.
@@ -348,7 +348,7 @@
\brief Algorithms for finding minimum cost spanning trees and arborescences.
This group contains the algorithms for finding minimum cost spanning
-trees and arborescences \ref clrs01algorithms.
+trees and arborescences \cite clrs01algorithms.
*/
/**
@@ -357,7 +357,7 @@
\brief Algorithms for finding maximum flows.
This group contains the algorithms for finding maximum flows and
-feasible circulations \ref clrs01algorithms, \ref amo93networkflows.
+feasible circulations \cite clrs01algorithms, \cite amo93networkflows.
The \e maximum \e flow \e problem is to find a flow of maximum value between
a single source and a single target. Formally, there is a \f$G=(V,A)\f$
@@ -373,13 +373,13 @@
LEMON contains several algorithms for solving maximum flow problems:
- \ref EdmondsKarp Edmonds-Karp algorithm
- \ref edmondskarp72theoretical.
+ \cite edmondskarp72theoretical.
- \ref Preflow Goldberg-Tarjan's preflow push-relabel algorithm
- \ref goldberg88newapproach.
+ \cite goldberg88newapproach.
- \ref DinitzSleatorTarjan Dinitz's blocking flow algorithm with dynamic trees
- \ref dinic70algorithm, \ref sleator83dynamic.
+ \cite dinic70algorithm, \cite sleator83dynamic.
- \ref GoldbergTarjan !Preflow push-relabel algorithm with dynamic trees
- \ref goldberg88newapproach, \ref sleator83dynamic.
+ \cite goldberg88newapproach, \cite sleator83dynamic.
In most cases the \ref Preflow algorithm provides the
fastest method for computing a maximum flow. All implementations
@@ -399,20 +399,20 @@
\brief Algorithms for finding minimum cost flows and circulations.
This group contains the algorithms for finding minimum cost flows and
-circulations \ref amo93networkflows. For more information about this
+circulations \cite amo93networkflows. For more information about this
problem and its dual solution, see: \ref min_cost_flow
"Minimum Cost Flow Problem".
LEMON contains several algorithms for this problem.
- \ref NetworkSimplex Primal Network Simplex algorithm with various
- pivot strategies \ref dantzig63linearprog, \ref kellyoneill91netsimplex.
+ pivot strategies \cite dantzig63linearprog, \cite kellyoneill91netsimplex.
- \ref CostScaling Cost Scaling algorithm based on push/augment and
- relabel operations \ref goldberg90approximation, \ref goldberg97efficient,
- \ref bunnagel98efficient.
+ relabel operations \cite goldberg90approximation, \cite goldberg97efficient,
+ \cite bunnagel98efficient.
- \ref CapacityScaling Capacity Scaling algorithm based on the successive
- shortest path method \ref edmondskarp72theoretical.
+ shortest path method \cite edmondskarp72theoretical.
- \ref CycleCanceling Cycle-Canceling algorithms, two of which are
- strongly polynomial \ref klein67primal, \ref goldberg89cyclecanceling.
+ strongly polynomial \cite klein67primal, \cite goldberg89cyclecanceling.
In general, \ref NetworkSimplex and \ref CostScaling are the most efficient
implementations.
@@ -430,7 +430,7 @@
data are required to be integer).
For more details about these implementations and for a comprehensive
-experimental study, see the paper \ref KiralyKovacs12MCF.
+experimental study, see the paper \cite KiralyKovacs12MCF.
It also compares these codes to other publicly available
minimum cost flow solvers.
*/
@@ -471,7 +471,7 @@
\brief Algorithms for finding minimum mean cycles.
This group contains the algorithms for finding minimum mean cycles
-\ref amo93networkflows, \ref karp78characterization.
+\cite amo93networkflows, \cite karp78characterization.
The \e minimum \e mean \e cycle \e problem is to find a directed cycle
of minimum mean length (cost) in a digraph.
@@ -487,11 +487,11 @@
function.
LEMON contains three algorithms for solving the minimum mean cycle problem:
-- \ref KarpMmc Karp's original algorithm \ref karp78characterization.
+- \ref KarpMmc Karp's original algorithm \cite karp78characterization.
- \ref HartmannOrlinMmc Hartmann-Orlin's algorithm, which is an improved
- version of Karp's algorithm \ref hartmann93finding.
+ version of Karp's algorithm \cite hartmann93finding.
- \ref HowardMmc Howard's policy iteration algorithm
- \ref dasdan98minmeancycle, \ref dasdan04experimental.
+ \cite dasdan98minmeancycle, \cite dasdan04experimental.
In practice, the \ref HowardMmc "Howard" algorithm turned out to be by far the
most efficient one, though the best known theoretical bound on its running
@@ -647,8 +647,8 @@
Various LP solvers could be used in the same manner with this
high-level interface.
-The currently supported solvers are \ref glpk, \ref clp, \ref cbc,
-\ref cplex, \ref soplex.
+The currently supported solvers are \cite glpk, \cite clp, \cite cbc,
+\cite cplex, \cite soplex.
*/
/**
diff -r eb2f9d453070 -r 1c978b5bcc65 doc/mainpage.dox.in
--- a/doc/mainpage.dox.in Sat Mar 16 14:11:32 2013 +0100
+++ b/doc/mainpage.dox.in Mon Mar 18 17:41:19 2013 +0100
@@ -25,7 +25,7 @@
and <b>O</b>ptimization in <b>N</b>etworks</i>.
It is a C++ template library providing efficient implementations of common
data structures and algorithms with focus on combinatorial optimization
-tasks connected mainly with graphs and networks \ref DezsoJuttnerKovacs11Lemon.
+tasks connected mainly with graphs and networks \cite DezsoJuttnerKovacs11Lemon.
<b>
LEMON is an <a class="el" href="http://opensource.org/">open source</a>
@@ -37,12 +37,12 @@
The project is maintained by the
<a href="http://www.cs.elte.hu/egres/">Egerváry Research Group on
-Combinatorial Optimization</a> \ref egres
+Combinatorial Optimization</a> \cite egres
at the Operations Research Department of the
<a href="http://www.elte.hu/en/">Eötvös Loránd University</a>,
Budapest, Hungary.
LEMON is also a member of the <a href="http://www.coin-or.org/">COIN-OR</a>
-initiative \ref coinor.
+initiative \cite coinor.
\section howtoread How to Read the Documentation
diff -r eb2f9d453070 -r 1c978b5bcc65 doc/min_cost_flow.dox
--- a/doc/min_cost_flow.dox Sat Mar 16 14:11:32 2013 +0100
+++ b/doc/min_cost_flow.dox Mon Mar 18 17:41:19 2013 +0100
@@ -26,7 +26,7 @@
The \e minimum \e cost \e flow \e problem is to find a feasible flow of
minimum total cost from a set of supply nodes to a set of demand nodes
in a network with capacity constraints (lower and upper bounds)
-and arc costs \ref amo93networkflows.
+and arc costs \cite amo93networkflows.
Formally, let \f$G=(V,A)\f$ be a digraph, \f$lower: A\rightarrow\mathbf{R}\f$,
\f$upper: A\rightarrow\mathbf{R}\cup\{+\infty\}\f$ denote the lower and
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/capacity_scaling.h
--- a/lemon/capacity_scaling.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/capacity_scaling.h Mon Mar 18 17:41:19 2013 +0100
@@ -66,8 +66,8 @@
///
/// \ref CapacityScaling implements the capacity scaling version
/// of the successive shortest path algorithm for finding a
- /// \ref min_cost_flow "minimum cost flow" \ref amo93networkflows,
- /// \ref edmondskarp72theoretical. It is an efficient dual
+ /// \ref min_cost_flow "minimum cost flow" \cite amo93networkflows,
+ /// \cite edmondskarp72theoretical. It is an efficient dual
/// solution method, which runs in polynomial time
/// \f$O(e\log U (n+e)\log n)\f$, where <i>U</i> denotes the maximum
/// of node supply and arc capacity values.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/cost_scaling.h
--- a/lemon/cost_scaling.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/cost_scaling.h Mon Mar 18 17:41:19 2013 +0100
@@ -91,8 +91,8 @@
///
/// \ref CostScaling implements a cost scaling algorithm that performs
/// push/augment and relabel operations for finding a \ref min_cost_flow
- /// "minimum cost flow" \ref amo93networkflows, \ref goldberg90approximation,
- /// \ref goldberg97efficient, \ref bunnagel98efficient.
+ /// "minimum cost flow" \cite amo93networkflows, \cite goldberg90approximation,
+ /// \cite goldberg97efficient, \cite bunnagel98efficient.
/// It is a highly efficient primal-dual solution method, which
/// can be viewed as the generalization of the \ref Preflow
/// "preflow push-relabel" algorithm for the maximum flow problem.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/cycle_canceling.h
--- a/lemon/cycle_canceling.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/cycle_canceling.h Mon Mar 18 17:41:19 2013 +0100
@@ -47,8 +47,8 @@
///
/// \ref CycleCanceling implements three different cycle-canceling
/// algorithms for finding a \ref min_cost_flow "minimum cost flow"
- /// \ref amo93networkflows, \ref klein67primal,
- /// \ref goldberg89cyclecanceling.
+ /// \cite amo93networkflows, \cite klein67primal,
+ /// \cite goldberg89cyclecanceling.
/// The most efficent one is the \ref CANCEL_AND_TIGHTEN
/// "Cancel-and-Tighten" algorithm, thus it is the default method.
/// It runs in strongly polynomial time O(n<sup>2</sup>e<sup>2</sup>log(n)),
@@ -131,13 +131,13 @@
SIMPLE_CYCLE_CANCELING,
/// The "Minimum Mean Cycle-Canceling" algorithm, which is a
/// well-known strongly polynomial method
- /// \ref goldberg89cyclecanceling. It improves along a
+ /// \cite goldberg89cyclecanceling. It improves along a
/// \ref min_mean_cycle "minimum mean cycle" in each iteration.
/// Its running time complexity is O(n<sup>2</sup>e<sup>3</sup>log(n)).
MINIMUM_MEAN_CYCLE_CANCELING,
/// The "Cancel-and-Tighten" algorithm, which can be viewed as an
/// improved version of the previous method
- /// \ref goldberg89cyclecanceling.
+ /// \cite goldberg89cyclecanceling.
/// It is faster both in theory and in practice, its running time
/// complexity is O(n<sup>2</sup>e<sup>2</sup>log(n)).
CANCEL_AND_TIGHTEN
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/grosso_locatelli_pullan_mc.h
--- a/lemon/grosso_locatelli_pullan_mc.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/grosso_locatelli_pullan_mc.h Mon Mar 18 17:41:19 2013 +0100
@@ -40,7 +40,7 @@
///
/// \ref GrossoLocatelliPullanMc implements the iterated local search
/// algorithm of Grosso, Locatelli, and Pullan for solving the \e maximum
- /// \e clique \e problem \ref grosso08maxclique.
+ /// \e clique \e problem \cite grosso08maxclique.
/// It is to find the largest complete subgraph (\e clique) in an
/// undirected graph, i.e., the largest set of nodes where each
/// pair of nodes is connected.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/hartmann_orlin_mmc.h
--- a/lemon/hartmann_orlin_mmc.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/hartmann_orlin_mmc.h Mon Mar 18 17:41:19 2013 +0100
@@ -98,7 +98,7 @@
///
/// This class implements the Hartmann-Orlin algorithm for finding
/// a directed cycle of minimum mean cost in a digraph
- /// \ref hartmann93finding, \ref dasdan98minmeancycle.
+ /// \cite hartmann93finding, \cite dasdan98minmeancycle.
/// This method is based on \ref KarpMmc "Karp"'s original algorithm, but
/// applies an early termination scheme. It makes the algorithm
/// significantly faster for some problem instances, but slower for others.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/howard_mmc.h
--- a/lemon/howard_mmc.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/howard_mmc.h Mon Mar 18 17:41:19 2013 +0100
@@ -98,7 +98,7 @@
///
/// This class implements Howard's policy iteration algorithm for finding
/// a directed cycle of minimum mean cost in a digraph
- /// \ref dasdan98minmeancycle, \ref dasdan04experimental.
+ /// \cite dasdan98minmeancycle, \cite dasdan04experimental.
/// This class provides the most efficient algorithm for the
/// minimum mean cycle problem, though the best known theoretical
/// bound on its running time is exponential.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/karp_mmc.h
--- a/lemon/karp_mmc.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/karp_mmc.h Mon Mar 18 17:41:19 2013 +0100
@@ -98,7 +98,7 @@
///
/// This class implements Karp's algorithm for finding a directed
/// cycle of minimum mean cost in a digraph
- /// \ref karp78characterization, \ref dasdan98minmeancycle.
+ /// \cite karp78characterization, \cite dasdan98minmeancycle.
/// It runs in time O(ne) and uses space O(n<sup>2</sup>+e).
///
/// \tparam GR The type of the digraph the algorithm runs on.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/network_simplex.h
--- a/lemon/network_simplex.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/network_simplex.h Mon Mar 18 17:41:19 2013 +0100
@@ -41,8 +41,8 @@
///
/// \ref NetworkSimplex implements the primal Network Simplex algorithm
/// for finding a \ref min_cost_flow "minimum cost flow"
- /// \ref amo93networkflows, \ref dantzig63linearprog,
- /// \ref kellyoneill91netsimplex.
+ /// \cite amo93networkflows, \cite dantzig63linearprog,
+ /// \cite kellyoneill91netsimplex.
/// This algorithm is a highly efficient specialized version of the
/// linear programming simplex method directly for the minimum cost
/// flow problem.
diff -r eb2f9d453070 -r 1c978b5bcc65 lemon/preflow.h
--- a/lemon/preflow.h Sat Mar 16 14:11:32 2013 +0100
+++ b/lemon/preflow.h Mon Mar 18 17:41:19 2013 +0100
@@ -102,8 +102,8 @@
///
/// This class provides an implementation of Goldberg-Tarjan's \e preflow
/// \e push-relabel algorithm producing a \ref max_flow
- /// "flow of maximum value" in a digraph \ref clrs01algorithms,
- /// \ref amo93networkflows, \ref goldberg88newapproach.
+ /// "flow of maximum value" in a digraph \cite clrs01algorithms,
+ /// \cite amo93networkflows, \cite goldberg88newapproach.
/// The preflow algorithms are the fastest known maximum
/// flow algorithms. The current implementation uses a mixture of the
/// \e "highest label" and the \e "bound decrease" heuristics.
diff -r eb2f9d453070 -r 1c978b5bcc65 scripts/bib2dox.py
--- a/scripts/bib2dox.py Sat Mar 16 14:11:32 2013 +0100
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,816 +0,0 @@
-#! /usr/bin/env python
-"""
- BibTeX to Doxygen converter
- Usage: python bib2dox.py bibfile.bib > bibfile.dox
-
- This file is a part of LEMON, a generic C++ optimization library.
-
- **********************************************************************
-
- This code is the modification of the BibTeX to XML converter
- by Vidar Bronken Gundersen et al.
- See the original copyright notices below.
-
- **********************************************************************
-
- Decoder for bibliographic data, BibTeX
- Usage: python bibtex2xml.py bibfile.bib > bibfile.xml
-
- v.8
- (c)2002-06-23 Vidar Bronken Gundersen
- http://bibtexml.sf.net/
- Reuse approved as long as this notification is kept.
- Licence: GPL.
-
- Contributions/thanks to:
- Egon Willighagen, http://sf.net/projects/jreferences/
- Richard Mahoney (for providing a test case)
-
- Editted by Sara Sprenkle to be more robust and handle more bibtex features.
- (c) 2003-01-15
-
- 1. Changed bibtex: tags to bibxml: tags.
- 2. Use xmlns:bibxml="http://bibtexml.sf.net/"
- 3. Allow spaces between @type and first {
- 4. "author" fields with multiple authors split by " and "
- are put in separate xml "bibxml:author" tags.
- 5. Option for Titles: words are capitalized
- only if first letter in title or capitalized inside braces
- 6. Removes braces from within field values
- 7. Ignores comments in bibtex file (including @comment{ or % )
- 8. Replaces some special latex tags, e.g., replaces ~ with ' '
- 9. Handles bibtex @string abbreviations
- --> includes bibtex's default abbreviations for months
- --> does concatenation of abbr # " more " and " more " # abbr
- 10. Handles @type( ... ) or @type{ ... }
- 11. The keywords field is split on , or ; and put into separate xml
- "bibxml:keywords" tags
- 12. Ignores @preamble
-
- Known Limitations
- 1. Does not transform Latex encoding like math mode and special
- latex symbols.
- 2. Does not parse author fields into first and last names.
- E.g., It does not do anything special to an author whose name is
- in the form LAST_NAME, FIRST_NAME
- In "author" tag, will show up as
- <bibxml:author>LAST_NAME, FIRST_NAME</bibxml:author>
- 3. Does not handle "crossref" fields other than to print
- <bibxml:crossref>...</bibxml:crossref>
- 4. Does not inform user of the input's format errors. You just won't
- be able to transform the file later with XSL
-
- You will have to manually edit the XML output if you need to handle
- these (and unknown) limitations.
-
-"""
-
-import string, re
-
-# set of valid name characters
-valid_name_chars = '[\w\-:]'
-
-#
-# define global regular expression variables
-#
-author_rex = re.compile('\s+and\s+')
-rembraces_rex = re.compile('[{}]')
-capitalize_rex = re.compile('({[^}]*})')
-
-# used by bibtexkeywords(data)
-keywords_rex = re.compile('[,;]')
-
-# used by concat_line(line)
-concatsplit_rex = re.compile('\s*#\s*')
-
-# split on {, }, or " in verify_out_of_braces
-delimiter_rex = re.compile('([{}"])',re.I)
-
-field_rex = re.compile('\s*(\w*)\s*=\s*(.*)')
-data_rex = re.compile('\s*(\w*)\s*=\s*([^,]*),?')
-
-url_rex = re.compile('\\\url\{([^}]*)\}')
-
-#
-# styles for html formatting
-#
-divstyle = 'margin-top: -4ex; margin-left: 10em;'
-
-#
-# return the string parameter without braces
-#
-def transformurls(str):
- return url_rex.sub(r'<a href="\1">\1</a>', str)
-
-#
-# return the string parameter without braces
-#
-def removebraces(str):
- return rembraces_rex.sub('', str)
-
-#
-# latex-specific replacements
-# (do this after braces were removed)
-#
-def latexreplacements(line):
- line = string.replace(line, '~', ' ')
- line = string.replace(line, '\\\'a', 'á')
- line = string.replace(line, '\\"a', 'ä')
- line = string.replace(line, '\\\'e', 'é')
- line = string.replace(line, '\\"e', 'ë')
- line = string.replace(line, '\\\'i', 'í')
- line = string.replace(line, '\\"i', 'ï')
- line = string.replace(line, '\\\'o', 'ó')
- line = string.replace(line, '\\"o', 'ö')
- line = string.replace(line, '\\\'u', 'ú')
- line = string.replace(line, '\\"u', 'ü')
- line = string.replace(line, '\\H o', 'õ')
- line = string.replace(line, '\\H u', 'ü') # ũ does not exist
- line = string.replace(line, '\\\'A', 'Á')
- line = string.replace(line, '\\"A', 'Ä')
- line = string.replace(line, '\\\'E', 'É')
- line = string.replace(line, '\\"E', 'Ë')
- line = string.replace(line, '\\\'I', 'Í')
- line = string.replace(line, '\\"I', 'Ï')
- line = string.replace(line, '\\\'O', 'Ó')
- line = string.replace(line, '\\"O', 'Ö')
- line = string.replace(line, '\\\'U', 'Ú')
- line = string.replace(line, '\\"U', 'Ü')
- line = string.replace(line, '\\H O', 'Õ')
- line = string.replace(line, '\\H U', 'Ü') # Ũ does not exist
-
- return line
-
-#
-# copy characters form a string decoding html expressions (&xyz;)
-#
-def copychars(str, ifrom, count):
- result = ''
- i = ifrom
- c = 0
- html_spec = False
- while (i < len(str)) and (c < count):
- if str[i] == '&':
- html_spec = True;
- if i+1 < len(str):
- result += str[i+1]
- c += 1
- i += 2
- else:
- if not html_spec:
- if ((str[i] >= 'A') and (str[i] <= 'Z')) or \
- ((str[i] >= 'a') and (str[i] <= 'z')):
- result += str[i]
- c += 1
- elif str[i] == ';':
- html_spec = False;
- i += 1
-
- return result
-
-
-#
-# Handle a list of authors (separated by 'and').
-# It gives back an array of the follwing values:
-# - num: the number of authors,
-# - list: the list of the author names,
-# - text: the bibtex text (separated by commas and/or 'and')
-# - abbrev: abbreviation that can be used for indicate the
-# bibliography entries
-#
-def bibtexauthor(data):
- result = {}
- bibtex = ''
- result['list'] = author_rex.split(data)
- result['num'] = len(result['list'])
- for i, author in enumerate(result['list']):
- # general transformations
- author = latexreplacements(removebraces(author.strip()))
- # transform "Xyz, A. B." to "A. B. Xyz"
- pos = author.find(',')
- if pos != -1:
- author = author[pos+1:].strip() + ' ' + author[:pos].strip()
- result['list'][i] = author
- bibtex += author + '#'
- bibtex = bibtex[:-1]
- if result['num'] > 1:
- ix = bibtex.rfind('#')
- if result['num'] == 2:
- bibtex = bibtex[:ix] + ' and ' + bibtex[ix+1:]
- else:
- bibtex = bibtex[:ix] + ', and ' + bibtex[ix+1:]
- bibtex = bibtex.replace('#', ', ')
- result['text'] = bibtex
-
- result['abbrev'] = ''
- for author in result['list']:
- pos = author.rfind(' ') + 1
- count = 1
- if result['num'] == 1:
- count = 3
- result['abbrev'] += copychars(author, pos, count)
-
- return result
-
-
-#
-# data = title string
-# @return the capitalized title (first letter is capitalized), rest are capitalized
-# only if capitalized inside braces
-#
-def capitalizetitle(data):
- title_list = capitalize_rex.split(data)
- title = ''
- count = 0
- for phrase in title_list:
- check = string.lstrip(phrase)
-
- # keep phrase's capitalization the same
- if check.find('{') == 0:
- title += removebraces(phrase)
- else:
- # first word --> capitalize first letter (after spaces)
- if count == 0:
- title += check.capitalize()
- else:
- title += phrase.lower()
- count = count + 1
-
- return title
-
-
-#
-# @return the bibtex for the title
-# @param data --> title string
-# braces are removed from title
-#
-def bibtextitle(data, entrytype):
- if entrytype in ('book', 'inbook'):
- title = removebraces(data.strip())
- else:
- title = removebraces(capitalizetitle(data.strip()))
- bibtex = title
- return bibtex
-
-
-#
-# function to compare entry lists
-#
-def entry_cmp(x, y):
- return cmp(x[0], y[0])
-
-
-#
-# print the XML for the transformed "filecont_source"
-#
-def bibtexdecoder(filecont_source):
- filecont = []
- file = []
-
- # want @<alphanumeric chars><spaces>{<spaces><any chars>,
- pubtype_rex = re.compile('@(\w*)\s*{\s*(.*),')
- endtype_rex = re.compile('}\s*$')
- endtag_rex = re.compile('^\s*}\s*$')
-
- bracefield_rex = re.compile('\s*(\w*)\s*=\s*(.*)')
- bracedata_rex = re.compile('\s*(\w*)\s*=\s*{(.*)},?')
-
- quotefield_rex = re.compile('\s*(\w*)\s*=\s*(.*)')
- quotedata_rex = re.compile('\s*(\w*)\s*=\s*"(.*)",?')
-
- for line in filecont_source:
- line = line[:-1]
-
- # encode character entities
- line = string.replace(line, '&', '&')
- line = string.replace(line, '<', '<')
- line = string.replace(line, '>', '>')
-
- # start entry: publication type (store for later use)
- if pubtype_rex.match(line):
- # want @<alphanumeric chars><spaces>{<spaces><any chars>,
- entrycont = {}
- entry = []
- entrytype = pubtype_rex.sub('\g<1>',line)
- entrytype = string.lower(entrytype)
- entryid = pubtype_rex.sub('\g<2>', line)
-
- # end entry if just a }
- elif endtype_rex.match(line):
- # generate doxygen code for the entry
-
- # enty type related formattings
- if entrytype in ('book', 'inbook'):
- entrycont['title'] = '<em>' + entrycont['title'] + '</em>'
- if not entrycont.has_key('author'):
- entrycont['author'] = entrycont['editor']
- entrycont['author']['text'] += ', editors'
- elif entrytype == 'article':
- entrycont['journal'] = '<em>' + entrycont['journal'] + '</em>'
- elif entrytype in ('inproceedings', 'incollection', 'conference'):
- entrycont['booktitle'] = '<em>' + entrycont['booktitle'] + '</em>'
- elif entrytype == 'techreport':
- if not entrycont.has_key('type'):
- entrycont['type'] = 'Technical report'
- elif entrytype == 'mastersthesis':
- entrycont['type'] = 'Master\'s thesis'
- elif entrytype == 'phdthesis':
- entrycont['type'] = 'PhD thesis'
-
- for eline in entrycont:
- if eline != '':
- eline = latexreplacements(eline)
-
- if entrycont.has_key('pages') and (entrycont['pages'] != ''):
- entrycont['pages'] = string.replace(entrycont['pages'], '--', '-')
-
- if entrycont.has_key('author') and (entrycont['author'] != ''):
- entry.append(entrycont['author']['text'] + '.')
- if entrycont.has_key('title') and (entrycont['title'] != ''):
- entry.append(entrycont['title'] + '.')
- if entrycont.has_key('journal') and (entrycont['journal'] != ''):
- entry.append(entrycont['journal'] + ',')
- if entrycont.has_key('booktitle') and (entrycont['booktitle'] != ''):
- entry.append('In ' + entrycont['booktitle'] + ',')
- if entrycont.has_key('type') and (entrycont['type'] != ''):
- eline = entrycont['type']
- if entrycont.has_key('number') and (entrycont['number'] != ''):
- eline += ' ' + entrycont['number']
- eline += ','
- entry.append(eline)
- if entrycont.has_key('institution') and (entrycont['institution'] != ''):
- entry.append(entrycont['institution'] + ',')
- if entrycont.has_key('publisher') and (entrycont['publisher'] != ''):
- entry.append(entrycont['publisher'] + ',')
- if entrycont.has_key('school') and (entrycont['school'] != ''):
- entry.append(entrycont['school'] + ',')
- if entrycont.has_key('address') and (entrycont['address'] != ''):
- entry.append(entrycont['address'] + ',')
- if entrycont.has_key('edition') and (entrycont['edition'] != ''):
- entry.append(entrycont['edition'] + ' edition,')
- if entrycont.has_key('howpublished') and (entrycont['howpublished'] != ''):
- entry.append(entrycont['howpublished'] + ',')
- if entrycont.has_key('volume') and (entrycont['volume'] != ''):
- eline = entrycont['volume'];
- if entrycont.has_key('number') and (entrycont['number'] != ''):
- eline += '(' + entrycont['number'] + ')'
- if entrycont.has_key('pages') and (entrycont['pages'] != ''):
- eline += ':' + entrycont['pages']
- eline += ','
- entry.append(eline)
- else:
- if entrycont.has_key('pages') and (entrycont['pages'] != ''):
- entry.append('pages ' + entrycont['pages'] + ',')
- if entrycont.has_key('year') and (entrycont['year'] != ''):
- if entrycont.has_key('month') and (entrycont['month'] != ''):
- entry.append(entrycont['month'] + ' ' + entrycont['year'] + '.')
- else:
- entry.append(entrycont['year'] + '.')
- if entrycont.has_key('note') and (entrycont['note'] != ''):
- entry.append(entrycont['note'] + '.')
- if entrycont.has_key('url') and (entrycont['url'] != ''):
- entry.append(entrycont['url'] + '.')
-
- # generate keys for sorting and for the output
- sortkey = ''
- bibkey = ''
- if entrycont.has_key('author'):
- for author in entrycont['author']['list']:
- sortkey += copychars(author, author.rfind(' ')+1, len(author))
- bibkey = entrycont['author']['abbrev']
- else:
- bibkey = 'x'
- if entrycont.has_key('year'):
- sortkey += entrycont['year']
- bibkey += entrycont['year'][-2:]
- if entrycont.has_key('title'):
- sortkey += entrycont['title']
- if entrycont.has_key('key'):
- sortkey = entrycont['key'] + sortkey
- bibkey = entrycont['key']
- entry.insert(0, sortkey)
- entry.insert(1, bibkey)
- entry.insert(2, entryid)
-
- # add the entry to the file contents
- filecont.append(entry)
-
- else:
- # field, publication info
- field = ''
- data = ''
-
- # field = {data} entries
- if bracedata_rex.match(line):
- field = bracefield_rex.sub('\g<1>', line)
- field = string.lower(field)
- data = bracedata_rex.sub('\g<2>', line)
-
- # field = "data" entries
- elif quotedata_rex.match(line):
- field = quotefield_rex.sub('\g<1>', line)
- field = string.lower(field)
- data = quotedata_rex.sub('\g<2>', line)
-
- # field = data entries
- elif data_rex.match(line):
- field = field_rex.sub('\g<1>', line)
- field = string.lower(field)
- data = data_rex.sub('\g<2>', line)
-
- if field == 'url':
- data = '\\url{' + data.strip() + '}'
-
- if field in ('author', 'editor'):
- entrycont[field] = bibtexauthor(data)
- line = ''
- elif field == 'title':
- line = bibtextitle(data, entrytype)
- elif field != '':
- line = removebraces(transformurls(data.strip()))
-
- if line != '':
- line = latexreplacements(line)
- entrycont[field] = line
-
-
- # sort entries
- filecont.sort(entry_cmp)
-
- # count the bibtex keys
- keytable = {}
- counttable = {}
- for entry in filecont:
- bibkey = entry[1]
- if not keytable.has_key(bibkey):
- keytable[bibkey] = 1
- else:
- keytable[bibkey] += 1
-
- for bibkey in keytable.keys():
- counttable[bibkey] = 0
-
- # generate output
- for entry in filecont:
- # generate output key form the bibtex key
- bibkey = entry[1]
- entryid = entry[2]
- if keytable[bibkey] == 1:
- outkey = bibkey
- else:
- outkey = bibkey + chr(97 + counttable[bibkey])
- counttable[bibkey] += 1
-
- # append the entry code to the output
- file.append('\\section ' + entryid + ' [' + outkey + ']')
- file.append('<div style="' + divstyle + '">')
- for line in entry[3:]:
- file.append(line)
- file.append('</div>')
- file.append('')
-
- return file
-
-
-#
-# return 1 iff abbr is in line but not inside braces or quotes
-# assumes that abbr appears only once on the line (out of braces and quotes)
-#
-def verify_out_of_braces(line, abbr):
-
- phrase_split = delimiter_rex.split(line)
-
- abbr_rex = re.compile( '\\b' + abbr + '\\b', re.I)
-
- open_brace = 0
- open_quote = 0
-
- for phrase in phrase_split:
- if phrase == "{":
- open_brace = open_brace + 1
- elif phrase == "}":
- open_brace = open_brace - 1
- elif phrase == '"':
- if open_quote == 1:
- open_quote = 0
- else:
- open_quote = 1
- elif abbr_rex.search(phrase):
- if open_brace == 0 and open_quote == 0:
- return 1
-
- return 0
-
-
-#
-# a line in the form phrase1 # phrase2 # ... # phrasen
-# is returned as phrase1 phrase2 ... phrasen
-# with the correct punctuation
-# Bug: Doesn't always work with multiple abbreviations plugged in
-#
-def concat_line(line):
- # only look at part after equals
- field = field_rex.sub('\g<1>',line)
- rest = field_rex.sub('\g<2>',line)
-
- concat_line = field + ' ='
-
- pound_split = concatsplit_rex.split(rest)
-
- phrase_count = 0
- length = len(pound_split)
-
- for phrase in pound_split:
- phrase = phrase.strip()
- if phrase_count != 0:
- if phrase.startswith('"') or phrase.startswith('{'):
- phrase = phrase[1:]
- elif phrase.startswith('"'):
- phrase = phrase.replace('"','{',1)
-
- if phrase_count != length-1:
- if phrase.endswith('"') or phrase.endswith('}'):
- phrase = phrase[:-1]
- else:
- if phrase.endswith('"'):
- phrase = phrase[:-1]
- phrase = phrase + "}"
- elif phrase.endswith('",'):
- phrase = phrase[:-2]
- phrase = phrase + "},"
-
- # if phrase did have \#, add the \# back
- if phrase.endswith('\\'):
- phrase = phrase + "#"
- concat_line = concat_line + ' ' + phrase
-
- phrase_count = phrase_count + 1
-
- return concat_line
-
-
-#
-# substitute abbreviations into filecont
-# @param filecont_source - string of data from file
-#
-def bibtex_replace_abbreviations(filecont_source):
- filecont = filecont_source.splitlines()
-
- # These are defined in bibtex, so we'll define them too
- abbr_list = ['jan','feb','mar','apr','may','jun',
- 'jul','aug','sep','oct','nov','dec']
- value_list = ['January','February','March','April',
- 'May','June','July','August','September',
- 'October','November','December']
-
- abbr_rex = []
- total_abbr_count = 0
-
- front = '\\b'
- back = '(,?)\\b'
-
- for x in abbr_list:
- abbr_rex.append( re.compile( front + abbr_list[total_abbr_count] + back, re.I ) )
- total_abbr_count = total_abbr_count + 1
-
-
- abbrdef_rex = re.compile('\s*@string\s*{\s*('+ valid_name_chars +'*)\s*=(.*)',
- re.I)
-
- comment_rex = re.compile('@comment\s*{',re.I)
- preamble_rex = re.compile('@preamble\s*{',re.I)
-
- waiting_for_end_string = 0
- i = 0
- filecont2 = ''
-
- for line in filecont:
- if line == ' ' or line == '':
- continue
-
- if waiting_for_end_string:
- if re.search('}',line):
- waiting_for_end_string = 0
- continue
-
- if abbrdef_rex.search(line):
- abbr = abbrdef_rex.sub('\g<1>', line)
-
- if abbr_list.count(abbr) == 0:
- val = abbrdef_rex.sub('\g<2>', line)
- abbr_list.append(abbr)
- value_list.append(string.strip(val))
- abbr_rex.append( re.compile( front + abbr_list[total_abbr_count] + back, re.I ) )
- total_abbr_count = total_abbr_count + 1
- waiting_for_end_string = 1
- continue
-
- if comment_rex.search(line):
- waiting_for_end_string = 1
- continue
-
- if preamble_rex.search(line):
- waiting_for_end_string = 1
- continue
-
-
- # replace subsequent abbreviations with the value
- abbr_count = 0
-
- for x in abbr_list:
-
- if abbr_rex[abbr_count].search(line):
- if verify_out_of_braces(line,abbr_list[abbr_count]) == 1:
- line = abbr_rex[abbr_count].sub( value_list[abbr_count] + '\g<1>', line)
- # Check for # concatenations
- if concatsplit_rex.search(line):
- line = concat_line(line)
- abbr_count = abbr_count + 1
-
-
- filecont2 = filecont2 + line + '\n'
- i = i+1
-
-
- # Do one final pass over file
-
- # make sure that didn't end up with {" or }" after the substitution
- filecont2 = filecont2.replace('{"','{{')
- filecont2 = filecont2.replace('"}','}}')
-
- afterquotevalue_rex = re.compile('"\s*,\s*')
- afterbrace_rex = re.compile('"\s*}')
- afterbracevalue_rex = re.compile('(=\s*{[^=]*)},\s*')
-
- # add new lines to data that changed because of abbreviation substitutions
- filecont2 = afterquotevalue_rex.sub('",\n', filecont2)
- filecont2 = afterbrace_rex.sub('"\n}', filecont2)
- filecont2 = afterbracevalue_rex.sub('\g<1>},\n', filecont2)
-
- return filecont2
-
-#
-# convert @type( ... ) to @type{ ... }
-#
-def no_outer_parens(filecont):
-
- # do checking for open parens
- # will convert to braces
- paren_split = re.split('([(){}])',filecont)
-
- open_paren_count = 0
- open_type = 0
- look_next = 0
-
- # rebuild filecont
- filecont = ''
-
- at_rex = re.compile('@\w*')
-
- for phrase in paren_split:
- if look_next == 1:
- if phrase == '(':
- phrase = '{'
- open_paren_count = open_paren_count + 1
- else:
- open_type = 0
- look_next = 0
-
- if phrase == '(':
- open_paren_count = open_paren_count + 1
-
- elif phrase == ')':
- open_paren_count = open_paren_count - 1
- if open_type == 1 and open_paren_count == 0:
- phrase = '}'
- open_type = 0
-
- elif at_rex.search( phrase ):
- open_type = 1
- look_next = 1
-
- filecont = filecont + phrase
-
- return filecont
-
-
-#
-# make all whitespace into just one space
-# format the bibtex file into a usable form.
-#
-def bibtexwasher(filecont_source):
-
- space_rex = re.compile('\s+')
- comment_rex = re.compile('\s*%')
-
- filecont = []
-
- # remove trailing and excessive whitespace
- # ignore comments
- for line in filecont_source:
- line = string.strip(line)
- line = space_rex.sub(' ', line)
- # ignore comments
- if not comment_rex.match(line) and line != '':
- filecont.append(' '+ line)
-
- filecont = string.join(filecont, '')
-
- # the file is in one long string
-
- filecont = no_outer_parens(filecont)
-
- #
- # split lines according to preferred syntax scheme
- #
- filecont = re.sub('(=\s*{[^=]*)},', '\g<1>},\n', filecont)
-
- # add new lines after commas that are after values
- filecont = re.sub('"\s*,', '",\n', filecont)
- filecont = re.sub('=\s*([\w\d]+)\s*,', '= \g<1>,\n', filecont)
- filecont = re.sub('(@\w*)\s*({(\s*)[^,\s]*)\s*,',
- '\n\n\g<1>\g<2>,\n', filecont)
-
- # add new lines after }
- filecont = re.sub('"\s*}','"\n}\n', filecont)
- filecont = re.sub('}\s*,','},\n', filecont)
-
-
- filecont = re.sub('@(\w*)', '\n@\g<1>', filecont)
-
- # character encoding, reserved latex characters
- filecont = re.sub('{\\\&}', '&', filecont)
- filecont = re.sub('\\\&', '&', filecont)
-
- # do checking for open braces to get format correct
- open_brace_count = 0
- brace_split = re.split('([{}])',filecont)
-
- # rebuild filecont
- filecont = ''
-
- for phrase in brace_split:
- if phrase == '{':
- open_brace_count = open_brace_count + 1
- elif phrase == '}':
- open_brace_count = open_brace_count - 1
- if open_brace_count == 0:
- filecont = filecont + '\n'
-
- filecont = filecont + phrase
-
- filecont2 = bibtex_replace_abbreviations(filecont)
-
- # gather
- filecont = filecont2.splitlines()
- i=0
- j=0 # count the number of blank lines
- for line in filecont:
- # ignore blank lines
- if line == '' or line == ' ':
- j = j+1
- continue
- filecont[i] = line + '\n'
- i = i+1
-
- # get rid of the extra stuff at the end of the array
- # (The extra stuff are duplicates that are in the array because
- # blank lines were removed.)
- length = len( filecont)
- filecont[length-j:length] = []
-
- return filecont
-
-
-def filehandler(filepath):
- try:
- fd = open(filepath, 'r')
- filecont_source = fd.readlines()
- fd.close()
- except:
- print 'Could not open file:', filepath
- washeddata = bibtexwasher(filecont_source)
- outdata = bibtexdecoder(washeddata)
- print '/**'
- print '\page references References'
- print
- for line in outdata:
- print line
- print '*/'
-
-
-# main program
-
-def main():
- import sys
- if sys.argv[1:]:
- filepath = sys.argv[1]
- else:
- print "No input file"
- sys.exit()
- filehandler(filepath)
-
-if __name__ == "__main__": main()
-
-
-# end python script