Merged from master version 0.9.5

Former-commit-id: 93d64a8

Author: reidmcy

README.md

@@ -4,6 +4,9 @@ metaknowledge is a Python3 library that simplifies bibliometric research using W
 
 The website can be found at [networkslab.org/metaknowledge](http://networkslab.org/metaknowledge/).
 
+## Currently in Beta
+metaknowledge is in the final stages of testing before a 1.0 release different versions may behave differently.
+
 ##Installing
 To install run `python3 setup.py install`
 

metaknowledge/__init__.py

@@ -29,7 +29,7 @@
 from .record import Record, recordParser, BadISIRecord
 from .citation import Citation, BadCitation, filterNonJournals
 from .recordCollection import RecordCollection, isiParser
-from .graphHelpers import write_edgeList, write_nodeAttributeFile, write_graph, read_graph, _ProgressBar, drop_edges, drop_nodesByDegree, drop_nodesByCount, graphStats
+from .graphHelpers import write_edgeList, write_nodeAttributeFile, write_graph, read_graph, _ProgressBar, drop_edges, drop_nodesByDegree, drop_nodesByCount, mergeGraphs, graphStats
 from .constants import VERBOSE_MODE
 #from .blondel import blondel, modularity
 from .diffusion import diffusionGraph, diffusionCount

metaknowledge/bin/metaknowledgeDocsGen.py

@@ -10,7 +10,7 @@
 import importlib
 import re
 
-documentedModules = ['tagProcessing', 'visual', 'journalAbbreviations']
+documentedModules = ['visual', 'journalAbbreviations', 'tagProcessing']
 
 docsPrefix = time.strftime("%Y-%m-%d-")
 
@@ -19,19 +19,38 @@
     'tagProcessing' : "All the tags and how they are handled",
     'journalAbbreviations' : "Look here to get your J9 database",
     'Citation' : "Citation are special, here is how they are handled",
-    'Record' : "The thing RecordCollections are made of",
+    'Record' : "What RecordCollections are made of",
     'RecordCollection' : "Where all the stuff happens, look here if you want to make things",
 }
 
+singleFileYAML = """---
+layout: page
+title: ""
+author:
+- name: Reid McIlroy-Young
+  department:
+  affiliation: University of Waterloo, Waterloo ON, Canada
+  email: rmcilroy@uwaterloo.ca
+- name: John McLevey
+  affiliation: University of Waterloo, Waterloo ON, Canada
+  email: john.mclevey@uwaterloo.ca
+shorttitle: metaknowledge
+search_omit: true
+---
+"""
+
 def makeBlurb(name):
     if name in blurbDict:
         return blurbDict[name]
     else:
         raise RuntimeError("{} needs a blurb".format(name))
 
 
-def makeHeader(title, excerpt, tags = (), weight = 10, layout = "doc"):
-    return """---
+def makeHeader(title, excerpt, tags = (), weight = 10, layout = "doc", singleFile = False):
+    if singleFile:
+        s = """\n---\n<a name="{0}"></a>\n""".format(title)
+    else:
+        s = """---
 layout: {4}
 title: {0}
 categories: docs
@@ -41,10 +60,12 @@ def makeHeader(title, excerpt, tags = (), weight = 10, layout = "doc"):
 ---
 <a name="{0}"></a>
 """.format(title, excerpt, ', '.join(tags), weight, layout)
+    return s
 
 def argumentParser():
     parser = argparse.ArgumentParser(description="A simple script to genrate docs for metaknowledge")
     parser.add_argument("-dir", "-d", default = os.path.normpath('.') ,nargs='?', help = 'Directory to write files to')
+    parser.add_argument("-single", "-s", action = 'store_true', default = False ,help = 'Write to only one file.')
     return parser.parse_args()
 
 def getLineNumber(objTuple):
@@ -71,12 +92,18 @@ def cleanargs(obj, basic = False):
 def makeUrls(s):
     return "[{0}]({{{{ site.baseurl }}}}{{% post_url /docs/{1}{2} %}}#{3})".format(s.group(1), docsPrefix, s.group(2), s.group(3))
 
-def cleanedDoc(obj, lvl):
+def makeSingleFileUrls(s):
+    return "[{0}](#{1})".format(s.group(1), s.group(3))
+
+def cleanedDoc(obj, lvl, singleFile = False):
     ds = inspect.getdoc(obj)
     lns = ds.split('\n')
     nds = ''
     for line in lns:
-        line = re.sub(r"\[(\S+)\]\(\#(\S+)\.(\S+)\)", makeUrls, line, count = 99)
+        if singleFile:
+            line = re.sub(r"\[(\S+)\]\(\#(\S+)\.(\S+)\)", makeSingleFileUrls, line, count = 99)
+        else:
+            line = re.sub(r"\[(\S+)\]\(\#(\S+)\.(\S+)\)", makeUrls, line, count = 99)
         if len(line) < 1:
             nds += '\n'
         elif line[0] == '#':
@@ -92,8 +119,11 @@ def cleanedDoc(obj, lvl):
             nds += line + '\n'
     return '{}\n\n'.format(nds)
 
-def makeTitle(module, name, args = ''):
-    s = '<a name="{1}"></a><small>{0}</small>**[<ins>{1}</ins>]({{{{ site.baseurl }}}}{{{{ page.url }}}}#{1})**{2}:\n\n'.format(module, name, args)
+def makeTitle(module, name, args = '', singleFile = False):
+    if singleFile:
+        s = '<a name="{1}"></a><small>{0}</small>**[<ins>{1}</ins>](#{1})**{2}:\n\n'.format(module, name, args)
+    else:
+        s = '<a name="{1}"></a><small>{0}</small>**[<ins>{1}</ins>]({{{{ site.baseurl }}}}{{{{ page.url }}}}#{1})**{2}:\n\n'.format(module, name, args)
     return s
 
 def makeLine():
@@ -109,34 +139,42 @@ def makeLine():
     ]
     return('<hr style="{}">'.format(''.join(style)))
 
-def makeTable(entries, header = '', prefix = ''):
+def makeTable(entries, header = '', prefix = '', withBlurbs = False, bigTable = False):
     ents = []
     if prefix:
         prefix = prefix + '.'
     for e in entries:
-        ents.append("""<li><article><a href="#{0}"><b>{0}</b>{1}</a></article></li>""".format(e[0], cleanargs(e[1], basic = True), prefix))
+        if withBlurbs:
+            ents.append("""<li><article><a href="#{0}"><b>{0}</b><span class="excerpt">{1}</span></a></article></li>""".format(e, blurbDict[e]))
+        elif bigTable:
+            if e[2] is None:
+                ents.append("""<li><article><a href="#{0}"><b>{0}</b>{1}</a></article></li>""".format(e[0], cleanargs(e[1], basic = True), prefix))
+            else:
+                ents.append("""<li><article><a href="#{0}"><small>{2}</small>.<b>{0}</b>{1}</a></article></li>""".format(e[0], cleanargs(e[1], basic = True), e[2]))
+        else:
+            ents.append("""<li><article><a href="#{0}"><b>{0}</b>{1}</a></article></li>""".format(e[0], cleanargs(e[1], basic = True), prefix))
     s = """{}\n\n<ul class="post-list">\n{}\n</ul>\n""".format(header,'\n'.join(ents))
     return s
 
-def writeFunc(fn, f, prefix = '', level = 5):
+def writeFunc(fn, f, prefix = '', level = 5, singleFile = False):
     f.write(makeLine() + "\n\n")
-    f.write(makeTitle(prefix, fn[0], cleanargs(fn[1])))
+    f.write(makeTitle(prefix, fn[0], cleanargs(fn[1]), singleFile = singleFile))
     try:
-        f.write(cleanedDoc(fn[1], lvl = level))
+        f.write(cleanedDoc(fn[1], lvl = level, singleFile = singleFile))
     except AttributeError:
         f.write("# Needs to be written\n\n")
         print("\033[93m{0}{1} had no docs\033[0m".format(prefix, fn[0]))
 
-def writeClass(cl, f, prefix = '', level = 4):
-    f.write(makeTitle(prefix, cl[0], cleanargs(cl[1].__init__)))
+def writeClass(cl, f, prefix = '', level = 4, singleFile = False):
+    f.write(makeTitle(prefix, cl[0], cleanargs(cl[1].__init__), singleFile = singleFile))
     try:
-        f.write(cleanedDoc(cl[1], lvl = level))
+        f.write(cleanedDoc(cl[1], lvl = level, singleFile = singleFile))
     except AttributeError:
         f.write("# Needs to be written\n\n")
         print("\033[93m{0}{1} had no docs\033[0m".format(prefix, cl[0]))
 
-def proccessClass(cl, f):
-    writeClass(cl, f)
+def proccessClass(cl, f, singleFile = False):
+    writeClass(cl, f, singleFile = singleFile)
     baseMems = inspect.getmembers(cl[1].__bases__[0])
     funcs = []
     for m in sorted(inspect.getmembers(cl[1]), key = getLineNumber):
@@ -146,23 +184,30 @@ def proccessClass(cl, f):
             funcs.append(m)
     f.write(makeTable(funcs, prefix = cl[0], header = "The {} class has the following methods:".format(cl[0])))
     for m in funcs:
-        writeFunc(m, f, prefix = '{}.'.format(cl[0]))
+        writeFunc(m, f, prefix = '{}.'.format(cl[0], singleFile = singleFile))
 
-def writeClassFile(name, typ):
+def writeClassFile(name, typ, targetFile = None, singleFile = False):
     fname = docsPrefix + "{}.md".format(name)
-    f = open(fname, 'w')
-    f.write(makeHeader(name, makeBlurb(name), tags = ["class"], weight = 2))
-    proccessClass((name, typ), f)
-    f.write("\n{% include docsFooter.md %}")
-    f.close()
+    if targetFile is not None:
+        f = targetFile
+    else:
+        f = open(fname, 'w')
+    f.write(makeHeader(name, makeBlurb(name), tags = ["class"], weight = 2, singleFile = singleFile))
+    proccessClass((name, typ), f, singleFile = singleFile)
+    if targetFile is None:
+        f.write("\n{% include docsFooter.md %}")
+        f.close()
 
-def writeModuleFile(mod):
+def writeModuleFile(mod, targetFile = None, singleFile = False):
     fname = docsPrefix + "{}.md".format(mod)
-    f = open(fname, 'w')
-    f.write(makeHeader(mod, makeBlurb(mod), tags = ["module"], weight = 3))
+    if targetFile is not None:
+        f = targetFile
+    else:
+        f = open(fname, 'w')
+    f.write(makeHeader(mod, makeBlurb(mod), tags = ["module"], weight = 3, singleFile = singleFile))
     f.write('\n# [{0}]({{{{ site.baseurl }}}}{{{{ page.url }}}}#{0})\n\n'.format(mod))
     module = importlib.import_module('metaknowledge.{}'.format(mod))
-    f.write(cleanedDoc(module, 3) + '\n\n')
+    f.write(cleanedDoc(module, 3, singleFile = singleFile) + '\n\n')
     funcs = []
     for m in sorted(inspect.getmembers(module, predicate = inspect.isfunction), key = getLineNumber):
         if inspect.isbuiltin(m[1]) or m[0][0] == '_':
@@ -173,17 +218,22 @@ def writeModuleFile(mod):
         f.write(makeTable(funcs, prefix = mod, header = "The {} module provides the following functions:".format(mod)))
     for fn in funcs:
         writeFunc(fn, f, prefix = "{}.".format(mod))
-    f.write("\n{% include docsFooter.md %}")
-    f.close()
-
-def writeMainBody(funcs, vrs, exceptions):
-    f = open(docsPrefix + "overview.md", 'w')
-    f.write(makeHeader("Overview", "The metaknowledge Package, a quick tour", tags = ["main"], weight = 0, layout = "doc"))
-    f.write(cleanedDoc(metaknowledge, 3) + '\n\n')
-    f.write("\n{% include docsFooter.md %}")
-    f.close()
-    f = open(docsPrefix + "metaknowledge.md", 'w')
-    f.write(makeHeader("Functions", "The metaknowledge functions, for filtering reading and writing graphs", tags = ["functions"], weight = 1, layout = "doc"))
+    if targetFile is None:
+        f.write("\n{% include docsFooter.md %}")
+        f.close()
+
+def writeMainBody(funcs, vrs, exceptions, targetFile = None, singleFile = False):
+    if targetFile:
+        f = targetFile
+    else:
+        f = open(docsPrefix + "overview.md", 'w')
+    f.write(makeHeader("Overview", "The metaknowledge Package, a quick tour", tags = ["main"], weight = 0, layout = "doc", singleFile = singleFile))
+    f.write(cleanedDoc(metaknowledge, 3, singleFile = singleFile) + '\n\n')
+    if targetFile is None:
+        f.write("\n{% include docsFooter.md %}")
+        f.close()
+        f = open(docsPrefix + "metaknowledge.md", 'w')
+    f.write(makeHeader("Base Functions", "The metaknowledge functions, for filtering reading and writing graphs", tags = ["functions"], weight = 1, layout = "doc", singleFile = singleFile))
     f.write(makeTable(funcs, header = "The functions provided by metaknowledge are:"))
     for fnc in funcs:
         writeFunc(fnc, f)
@@ -194,8 +244,9 @@ def writeMainBody(funcs, vrs, exceptions):
         else:
             f.write(makeLine() + "\n\n")
         proccessClass(excpt, f)
-    f.write("\n{% include docsFooter.md %}")
-    f.close()
+    if targetFile is None:
+        f.write("\n{% include docsFooter.md %}")
+        f.close()
 
 def main(args):
     wDir = os.path.expanduser(os.path.normpath(args.dir))
@@ -223,11 +274,39 @@ def main(args):
             funcs.append(m)
         else:
             vrs.append(m)
-    writeMainBody(funcs, vrs, exceptions)
+    if args.single:
+        f = open("metaknowledgeFull.md",'w')
+        f.write(singleFileYAML)
+        f.write(makeTable([c[0] for c in classes] + documentedModules, header = "The classes and modules of metaknowledge are:", withBlurbs = True))
+        single = True
+        bigTableEntries = [(f[0], f[1], None) for f in funcs]
+        for cls in classes:
+            baseMems = inspect.getmembers(cls[1].__bases__[0])
+            for m in sorted(inspect.getmembers(cls[1]), key = getLineNumber):
+                if m[0][0] == '_' or m in baseMems:
+                    pass
+                elif inspect.isfunction(m[1]):
+                    bigTableEntries.append((m[0], m[1], cls[0]))
+        for mod in documentedModules:
+            module = importlib.import_module('metaknowledge.{}'.format(mod))
+            for m in sorted(inspect.getmembers(module, predicate = inspect.isfunction), key = getLineNumber):
+                if inspect.isbuiltin(m[1]) or m[0][0] == '_':
+                    pass
+                elif inspect.isfunction(m[1]):
+                    bigTableEntries.append((m[0], m[1], mod))
+        print(len(bigTableEntries))
+        f.write(makeTable(bigTableEntries, header = '<a name="fulllist"></a>All the functions and methods of metaknowledge are as follows:', bigTable = True))
+    else:
+        single = False
+        f = None
+    writeMainBody(funcs, vrs, exceptions, targetFile = f, singleFile = single)
     for cls in classes:
-        writeClassFile(*cls)
+        writeClassFile(*cls, targetFile = f, singleFile = single)
     for mod in documentedModules:
-        writeModuleFile(mod)
+        writeModuleFile(mod, targetFile = f, singleFile = single)
+    if args.single:
+        f.write("\n{% include docsFooter.md %}")
+        f.close
 
 def mkDocs():
     args = argumentParser()

metaknowledge/citation.py

@@ -167,6 +167,27 @@ def getID(self):
         else:
             return "{0}, {1}, {2}".format(self.author, self.year, self.journal)
 
+    def allButDOI(self):
+        """
+        Returns a string of the normalized values from the Citation excluding the DOI number. Equivalent to getting the ID with [`getID()`](#Citation.getID) then appending the extra values from [`getExtra()`](#Citation.getExtra) and then removing the substring containing the DOI number.
+
+        # Returns
+
+        `str`
+
+        > A string containing the data of the Citation.
+        """
+        extraTags = ['V', 'P', 'misc']
+        s = self.getID()
+        extras = []
+        for tag in extraTags:
+            if getattr(self, tag):
+                extras.append(str(getattr(self, tag)))
+        if len(extras) > 0:
+            return "{0}, {1}".format(s, ', '.join(extras))
+        else:
+            return s
+
     def getExtra(self):
         """
         Returns any V, P, DOI or misc values as a string. These are all the values not returned by [`getID()`](#Citation.getID).
@@ -176,7 +197,7 @@ def getExtra(self):
         `str`
 
         > A string containing the data not in the ID of the Citation.
-         """
+        """
         extraTags = ['V', 'P', 'DOI', 'misc']
         retVal = ""
         for tag in extraTags: