Add BibTeX file, by-author listing

svn:r11

5 files changed, 171 insertions, 169 deletions

diff --git a/BibTeX.py b/BibTeX.py
index 9b0d38c..f30e4ce 100644
--- a/BibTeX.py
+++ b/BibTeX.py
@@ -14,7 +14,14 @@ __all__ = ( 'ParseError', 'BibTeX', 'BibTeXEntry', 'htmlize',
 MONTHS = [ None,
            "January", "February", "March", "April", "May", "June",
            "July", "August", "September", "October", "November", "December"]
-            
+
+def url_untranslate(s):
+    s = s.replace(" ", "+")
+    s = re.sub(r'([%<>])',
+               lambda m: "%%%02x"%ord(m.group(1)),
+               s)
+    return s
+
 class ParseError(Exception):
     pass
 
@@ -84,6 +91,29 @@ def sortEntriesBy(entries, field, default):
     tmp.sort()
     return [ t[1] for t in tmp ]
 
+def splitEntriesByAuthor(entries):
+    entries = sortEntriesByDate(entries)
+    result = {} # Name in sorting order -> entries
+    htmlResult = {} # name in sorting order -> Full name
+    url_map = {} # Full name -> Url
+    for ent in entries:
+        for a in ent.parsedAuthor:
+            sortkey = txtize(" ".join(a.von+a.last+a.first+a.jr))
+            secname = " ".join(a.first+a.von+a.last)
+            if a.jr:
+                secname += ", "+a.jr
+            secname = htmlize(secname)
+            url = author_url(secname)
+            if url:
+                url_map[secname] = url
+
+            htmlResult[sortkey] = secname
+            result.setdefault(sortkey, []).append(ent)
+    sortnames = result.keys()
+    sortnames.sort()
+    sections = [ (htmlResult[n], result[n]) for n in sortnames ]
+    return sections, url_map
+
 def sortEntriesByAuthor(entries):
     tmp = []
     for ent in entries:
@@ -131,7 +161,7 @@ class BibTeXEntry:
         self.entries[k] = v
     def __str__(self):
         return self.format(70,1)
-    def format(self, width=70,v=0):
+    def format(self, width=70, indent=8, v=0):
         d = ["@%s{%s,\n" % (self.type, self.key)]
         if v:
             df = DISPLAYED_FIELDS[:]
@@ -145,8 +175,8 @@ class BibTeXEntry:
                 continue
             v = self.entries[f]
             d.append("  ")
-            s = "%s = {%s}\n" % (f, v)
-            d.append(_split(s,width))
+            s = "%s = {%s},\n" % (f, v)
+            d.append(_split(s,width,indent))
         d.append("}\n")
         return "".join(d)
     def resolve(self):
@@ -259,10 +289,11 @@ class BibTeXEntry:
 
         res[0:0] = ["<span class='biblio'>"]
         res.append("</span>")
-        
-        res.append(" <span class='availability'>"
-                   "(<a href='__'>BibTeX&nbsp;entry</a>)"
-                   "</span>")
+
+        bibtexurl = "./bibtex.html#%s"%url_untranslate(self.key)
+        res.append((" <span class='availability'>"
+                   "(<a href='%s'>BibTeX&nbsp;entry</a>)"
+                   "</span>") %bibtexurl)
         return htmlize("".join(res))
 
     def to_html(self):
@@ -285,21 +316,8 @@ class BibTeXEntry:
         res.append("<br><span class='author'>by ")
 
         #res.append("\n<!-- %r -->\n" % self.parsedAuthor)
-        htmlAuthors = []
-        for author in self.parsedAuthor:
-            f,v,l,j = author.first,author.von,author.last,author.jr
-            a = " ".join(f+v+l)
-            if j:
-                a = "%s, %s" %(a,j)
-            a = htmlize(a)
-            htmlAuthor = None
-            for pat, url in config.AUTHOR_RE_LIST:
-                if pat.search(a):
-                    htmlAuthor = '<a href="%s">%s</a>' % (url, a)
-                    break
-            if not htmlAuthor:
-                htmlAuthor = a
-            htmlAuthors.append(htmlAuthor)
+        htmlAuthors = [ htmlize_author(a) for a in self.parsedAuthor ]
+
         if len(htmlAuthors) == 1:
             res.append(htmlAuthors[0])
         elif len(htmlAuthors) == 2:
@@ -319,8 +337,12 @@ class BibTeXEntry:
 RE_LONE_AMP = re.compile(r'&([^a-z0-9])')
 RE_LONE_I = re.compile(r'\\i([^a-z0-9])')
 RE_ACCENT = re.compile(r'\\([\'`~^"])(.)')
-ACCENT_MAP = { "'": 'acute', "`" : 'grave', "~": 'tilde',
-               "^": 'circ',  '"' : 'uml' }
+ACCENT_MAP = { "'" : 'acute',
+               "`" : 'grave',
+               "~" : 'tilde',
+               "^" : 'circ',
+               '"' : 'uml',
+               }
 RE_TEX_CMD = re.compile(r"(?:\\[a-zA-Z@]+|\\.)")
 RE_PAGE_SPAN = re.compile(r"(\d)--(\d)")
 def htmlize(s):
@@ -334,6 +356,25 @@ def htmlize(s):
     s = RE_PAGE_SPAN.sub(lambda m: "%s-%s"%(m.groups()), s)
     return s
 
+def htmlize_author(author):
+    f,v,l,j = author.first,author.von,author.last,author.jr
+    a = " ".join(f+v+l)
+    if j:
+        a = "%s, %s" %(a,j)
+    a = htmlize(a)
+    u = author_url(a)
+    if u:
+        return "<a href='%s'>%s</a>"%(u,a)
+    else:
+        return a
+    return a
+
+def author_url(author):
+    for pat, url in config.AUTHOR_RE_LIST:
+        if pat.search(author):
+            return url
+    return None
+
 def txtize(s):
     s = RE_LONE_I.sub(lambda m: "%s" % m.group(1), s)
     s = RE_ACCENT.sub(lambda m: "%s" % m.group(2), s)
@@ -359,19 +400,25 @@ class ParsedAuthor:
     def __str__(self):
         return " ".join(self.first+self.von+self.last+self.jr)
 
-def _split(s,w=79):
+def _split(s,w=79,indent=8):
     r = []
-    s = s.replace("\n", " ")
+    s = re.sub(r"\s+", " ", s)
+    first = 1
+    indentation = ""
     while len(s) > w:
         for i in xrange(w-1, 0, -1):
             if s[i] == ' ':
-                r.append(s[:i])
+                r.append(indentation+s[:i])
                 s = s[i+1:]
                 break
         else:
-            r.append(s[:w])
+            r.append(indentation+s[:w])
             s = s[w:]
-    r.append(s)
+        if first:
+            first = 0
+            w -= indent
+            indentation = " "*indent
+    r.append(indentation+s)
     r.append("")
     return "\n".join(r)
             
diff --git a/_template_.html b/_template_.html
index ae9b05e..473fe4c 100644
--- a/_template_.html
+++ b/_template_.html
@@ -4,7 +4,7 @@
 <meta http-equiv="Content-Style-Type" content="text/css">
 
 <!-- *** I AM MACHINE GENERATED! DO NOT EDIT ME!
-  -- *** EDIT THE .bib FILE INSTEAD!
+  -- *** EDIT THE .bib FILE or _template_.html INSTEAD!
   --
   -- Generated by `%(command_line)s'
   -- (c) Eddie Kohler 1999-2000, Nick Mathewson 2003 -->
@@ -18,122 +18,26 @@
 <body bgcolor="#ffffff" text="#000000" link="#bb0000" vlink="#990099"
 alink="#ff9900" marginheight="0" marginwidth="0">
 
-<table cellspacing="0" cellpadding="0" border="0" align="center">
-
-<!-- 
-<tr valign="top">
-<td rowspan="5" width="134"><div align="right"><a href="/"><img
-src="/img/pdostab.gif" width="134" height="61" border="0" 
-alt="PDOS Home"></a></div></td> 
-<td rowspan="5" width="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-<td bgcolor="#ffffcc"><p><br></p></td>
-<td bgcolor="#ffffcc"><p><br></p></td>
-<td bgcolor="#ffffcc"><p><br></p></td>
-<td rowspan="3" width="8" bgcolor="#ffffcc"><img src="/img/emptydot.gif"
-width="8" height="1" alt=""></td>
-<td rowspan="3" width="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td bgcolor="#ffffcc"><p>&nbsp;&nbsp;<a href="http://web.mit.edu/">MIT</a>&nbsp;&gt;&nbsp;<a href="http://www.lcs.mit.edu/">LCS</a>&nbsp;&gt;&nbsp;<a href="/">PDOS&nbsp;Home</a>&nbsp;&gt;&nbsp;</p></td>
-<td bgcolor="#ffffcc"><p><b>Publications</b>&nbsp;&gt;&nbsp;</p></td>
-<td bgcolor="#ffffcc"><p><b>By&nbsp;subject</b></p></td>
-</tr>
-
-<tr valign="top">
-<td bgcolor="#ffffcc"><p><br></p></td>
-<td bgcolor="#ffffcc"><p class="crumbbreadth">
-<a href="projects.html">Projects</a><br>
-<a href="people.html">People</a><br>
-<a href="software.html">Software</a></p></td>
-<td bgcolor="#ffffcc"><p class="crumbbreadth">
-<a href="/cgi-bin/pubs-date.cgi">By date</a></p></td>
-</tr>
-
-<tr valign="top">
-<td colspan="2" height="8" bgcolor="#ffffcc"><img src="/img/emptydot.gif"
-width="1" height="8" alt=""></td>
-<td colspan="1" height="8" bgcolor="#ffffcc"><img src="/img/emptydot.gif"
-width="100" height="8" alt=""></td>
-<td colspan="2" rowspan="2" width="9" height="9" bgcolor="#ffffcc"><img
-src="/img/whitecorner.gif" width="9" height="9" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td colspan="3" height="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-</tr>
-
-</table>
--->
-
 <h1 align="center">Anonymity bibliography</h1>
 <p align="center">%(choices)s</p>
 
-<table cellspacing="0" cellpadding="0" border="0" width="100">
-
-<tr valign="top">
-<td width="10%%" height="24"><br></td>
-</tr>
-
-<tr valign="top">
-<td><div align="right">
-<table cellspacing="0" cellpadding="0" border="0" width="161">
-
-<tr valign="top">
-<td rowspan="6" width="8"><img src="/img/emptydot.gif"
-width="8" height="1" alt=""></td>
-<td colspan="4" height="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td rowspan="5" width="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-
-<td width="8" bgcolor="#ccffff"><img src="/img/emptydot.gif"
-width="8" height="1" alt=""></td>
-<td rowspan="3" width="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-<td rowspan="3" width="12"><img src="/img/emptydot.gif"
-width="12" height="1" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td colspan="2" height="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-</tr>
-
+<!-- Table 1: contains the sidebar and the body. -->
+<table cellspacing="3" cellpadding="0" border="0" align="center" width="100%%">
 <tr valign="top">
-<td bgcolor="#ccffff"><p class="l1"><br><form action="/cgi-bin/pubs-date.cgi"
-method="get"><strong>%(sectiontypes)s:</strong><br>
+<td>
 
+<!-- Table 2: The sidebar-->
+<table align="right" cellspacing="0" cellpadding="5" width="100" 
+     class="sidebar">
+<tr valign="top"><td><p 
+class="l1"><strong>%(sectiontypes)s:</strong><br>
 %(sections)s
-
 </p></td>
 
-<td width="8" bgcolor="#ccffff"><img src="/img/emptydot.gif"
-width="8" height="1" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td height="8" bgcolor="#ccffff"><img src="/img/emptydot.gif"
-width="1" height="8" alt=""></td>
-<td colspan="2" rowspan="2" width="9" height="9" bgcolor="#ccffff"><img
-src="/img/whitecorner.gif" width="9" height="9" alt=""></td>
-</tr>
-
-<tr valign="top">
-<td height="1" bgcolor="#92a6a4"><img src="/img/emptydot.gif"
-width="1" height="1" alt=""></td>
-</tr>
-
-</table>
-</div></td>
+</table><!-- End of table 2 -->
+</td>
 
-<td width="75%%">
+<td width="85%%">
 
 <h2>Publications by %(field)s</h2>
 
@@ -143,11 +47,10 @@ width="1" height="1" alt=""></td>
 
 </td>
 
-<td width="15%%"><br></td>
+<td width="5%%"><br></td>
 
 </tr>
-</table>
+</table><!-- End of table 1 --> 
 
 </body>
 </html>
-
diff --git a/css/main.css b/css/main.css
index e874ca4..8b336c9 100644
--- a/css/main.css
+++ b/css/main.css
@@ -77,9 +77,13 @@ H1 A, H2 A, H3 A, H4 A, H5 A, H6 A {
 }
 
 H1 {
-  color: #338;
+  color: #00B;
 }
 
 H2 {
   color: #006;
 }
+
+H3 {
+  color: #006;
+}
diff --git a/css/pubs.css b/css/pubs.css
index 7281a1d..971616e 100644
--- a/css/pubs.css
+++ b/css/pubs.css
@@ -41,3 +41,24 @@ P.l2 {
   margin-top: 0.3em;
   margin-bottom: 0.3em;
 }
+
+TABLE.sidebar {
+  border-width: 2;
+  border-color: black;
+  border-style: solid;
+  background-color: #CFF;
+}
+
+TD.bibtex {
+  font-family: lucidatypewriter, "Lucida Typewriter", Monaco, "Lucida Sans Unicode", monospace;  
+  border-width: 2;
+  font-weight: normal; 
+  border-color: black;
+  border-style: solid;
+  background-color: #DFF;
+}
+
+PRE.bibtex {
+  font-family: lucidatypewriter, "Lucida Typewriter", Monaco, "Lucida Sans Unicode", monospace; 
+  font-size: smaller;
+}
diff --git a/writeHTML.py b/writeHTML.py
index 8037abd..2ffd7c7 100644
--- a/writeHTML.py
+++ b/writeHTML.py
@@ -5,36 +5,30 @@ import re
 import BibTeX
 import config
 
-TEMPLATE_S, TEMPLATE_E = None, None
+def getTemplate(name):
+    f = open(name+".html")
+    template = f.read()
+    f.close()
+    template_s, template_e = template.split("%(entries)s")
+    return template_s, template_e
 
-def getTemplate():
-    global TEMPLATE_S
-    global TEMPLATE_E
-    if not TEMPLATE_S:
-        f = open("_template_.html")
-        template = f.read()
-        f.close()
-        TEMPLATE_S, TEMPLATE_E = template.split("%(entries)s")
-    return TEMPLATE_S, TEMPLATE_E
-
-def url_untranslate(s):
-    s = s.replace(" ", "+")
-    s = re.sub(r'([%<>])',
-               lambda m: "%%%02x"%ord(m.group(1)),
-               s)
-    return s
-
-def writeBody(f, sections):
+def writeBody(f, sections, section_urls):
     '''f: an open file 
        sections: list of (sectionname, [list of BibTeXEntry])'''
     for s, entries in sections:
-        print >>f, ('<h2><a name="%s">%s</a></h2>'%(url_untranslate(s),s))
+        u = section_urls.get(s)
+        if u:
+            print >>f, ('<h3><a name="%s"><a href="%s">%s</a></a></h3>'%(
+                u, BibTeX.url_untranslate(s),s))
+        else:
+            print >>f, ('<h3><a name="%s">%s</a></h3>'%(
+                BibTeX.url_untranslate(s),s))
         print >>f, "<ul class='expand'>"
         for e in entries:
             print >>f, e.to_html()
         print >>f, "</ul>"
 
-def writeHTML(f, sections, sectionType, fieldName, choices):
+def writeHTML(f, sections, sectionType, fieldName, choices, section_urls={}):
     """sections: list of (sectionname, [list of BibTeXEntry])'''
        sectionType: str
        fieldName: str
@@ -43,7 +37,7 @@ def writeHTML(f, sections, sectionType, fieldName, choices):
     secStr = []
     for s, _ in sections:
         secStr.append("<p class='l2'><a href='#%s'>%s</a></p>\n"%
-                      ((url_untranslate(s),s)))
+                      ((BibTeX.url_untranslate(s),s)))
     secStr = "".join(secStr)
     
     # 
@@ -63,9 +57,9 @@ def writeHTML(f, sections, sectionType, fieldName, choices):
                'sections' : secStr,
          }
 
-    header, footer = getTemplate()
+    header, footer = getTemplate("_template_")
     print >>f, header%fields
-    writeBody(f, sections)
+    writeBody(f, sections, section_urls)
     print >>f, footer%fields
     
 bib = BibTeX.parseFile(config.MASTER_BIB)
@@ -86,7 +80,9 @@ entries = [ (s, BibTeX.sortEntriesByAuthor(ents))
 f = open("topic.html", 'w')
 writeHTML(f, entries, "Topics", "topic",
           (("By topic", None),
-           ("By date", "./date.html")))
+           ("By date", "./date.html"),
+           ("By author", "./author.html")
+           ))
 f.close()
 
 ## By date.
@@ -107,7 +103,38 @@ if entries[-1][0] == 'Unknown':
 f = open("date.html", 'w')
 writeHTML(f, entries, "Years", "date",
           (("By topic", "./topic.html"),
-           ("By date", None)))
+           ("By date", None),
+           ("By author", "./author.html")
+           ))
+f.close()
+
+## By author
+entries, url_map = BibTeX.splitEntriesByAuthor(bib.entries)
+
+f = open("author.html", 'w')
+writeHTML(f, entries, "Authors", "author",
+          (("By topic", "./topic.html"),
+           ("By date", "./date.html"),
+           ("By author", None),
+          ),
+          url_map)
+f.close()
+
+## The big BibTeX file
+
+entries = bib.entries[:]
+entries = [ (ent.key, ent) for ent in entries ]
+entries.sort()
+entries = [ ent[1] for ent in entries ]
+header,footer = getTemplate("_template_bibtex")
+f = open("bibtex.html", 'w')
+print >>f, header % { 'command_line' : "" }
+for ent in entries:
+    print >>f, (
+        ("<tr><td class='bibtex'><a name='%s'>%s</a>"
+        "<pre class='bibtex'>%s</pre></td></tr>")
+        %(BibTeX.url_untranslate(ent.key), ent.key, ent.format(90,8,1)))
+    ##print >>f, "<p><pre>%s</pre></p>" % ent.format(80,1)
+print >>f, footer
 f.close()
 
-## The big BibTeX