pyDiffTools 0.1.6__py3-none-any.whl

pydifftools/comment_functions.py

@@ -0,0 +1,39 @@
+def comment_definition(commandname, name, comment_text):
+    return r"\newcommand{\%s}{%s}" % (commandname, comment_text) + "\n"
+
+
+def generate_alphabetnumber(x):
+    if x < 26:
+        return chr(ord("a") + x)
+    else:
+        higher_places = x // 26
+        return generate_alphabetnumber(
+            higher_places - 1
+        ) + generate_alphabetnumber(x - higher_places * 26)
+
+
+def matchingbrackets(content, startpoint, bracket_type):
+    if bracket_type == "(":
+        opening = "("
+        closing = ")"
+    elif bracket_type == "[":
+        opening = "["
+        closing = "]"
+    elif bracket_type == "{":
+        opening = "{"
+        closing = "}"
+    else:
+        raise ValueError("I didn't understand the type of bracket!")
+    first = (
+        False  # of course, don't want to break until we've found at least one
+    )
+    level = 0
+    for j in range(startpoint, len(content)):
+        if content[j] == opening:
+            if level == 0:
+                first = j
+            level += 1
+        if content[j] == closing:
+            level -= 1
+        if level == 0 and first:
+            return first, j

pydifftools/continuous.py

@@ -0,0 +1,166 @@
+"""
+this requires geckodriver to be installed and available
+"""
+
+import time
+from selenium import webdriver
+import selenium
+import subprocess, sys, os, psutil, re
+from watchdog.observers import Observer
+from watchdog.events import FileSystemEventHandler
+
+
+def run_pandoc(filename, html_file):
+    if os.path.exists("MathJax-3.1.2"):
+        has_local_jax = True
+    else:
+        has_local_jax = False
+        print("you don't have a local copy of mathjax.  You could get it with")
+        print(
+            "wget https://github.com/mathjax/MathJax/archive/refs/tags/3.1.2.zip"
+        )
+        print("and then unzip")
+    current_dir = os.getcwd()
+    localfiles = {}
+    for k in ["csl", "bib"]:
+        localfiles[k] = [
+            f for f in os.listdir(current_dir) if f.endswith("." + k)
+        ]
+        if len(localfiles[k]) == 1:
+            localfiles[k] = localfiles[k][0]
+        else:
+            raise ValueError(
+                f"You have more than one (or no) {k} file in this directory!"
+                " Get rid of all but one! of "
+                + "and".join(localfiles[k])
+            )
+    command = [
+        "pandoc",
+        "--bibliography",
+        localfiles["bib"],
+        f"--csl={localfiles['csl']}",
+        "--filter",
+        "pandoc-crossref",
+        "--citeproc",
+        "--mathjax",
+        "--number-sections",
+        "--toc",
+        "-s",
+        "-o",
+        html_file,
+        filename,
+    ]
+    # command = ['pandoc', '-s', '--mathjax', '-o', html_file, filename]
+    print("running:",' '.join(command))
+    subprocess.run(
+        command,
+    )
+    print("running:\n", command)
+    if has_local_jax:
+        # {{{ for slow internet connection, remove remote files
+        with open(html_file, encoding="utf-8") as fp:
+            text = fp.read()
+        patterns = [
+            r"<script.{0,20}?cdn\.jsdeli.{0,20}?mathjax.{0,60}?script>",
+            r"<script.{0,20}?https...polyfill.{0,60}?script>",
+        ]
+        for j in patterns:
+            text = re.sub(j, "", text, flags=re.DOTALL)
+        with open(html_file, "w", encoding="utf-8") as fp:
+            fp.write(text)
+        # }}}
+    return
+
+
+class Handler(FileSystemEventHandler):
+    def __init__(self, filename, observer):
+        self.observer = observer
+        self.filename = filename
+        self.html_file = filename.rsplit(".", 1)[0] + ".html"
+        # self.firefox = webbrowser.get('firefox')
+        # self.firefox = webdriver.Firefox() # requires geckodriver
+        self.init_firefox()
+
+    def init_firefox(self):
+        self.firefox = webdriver.Chrome()  # requires chromium
+        run_pandoc(self.filename, self.html_file)
+        if not os.path.exists(self.html_file):
+            print("html doesn't exist")
+        self.append_autorefresh()
+        # self.firefox.open_new_tab(self.html_file)
+        self.firefox.get("file://" + os.path.abspath(self.html_file))
+
+    def on_modified(self, event):
+        # print("modification event")
+        if os.path.normpath(
+            os.path.abspath(event.src_path)
+        ) == os.path.normpath(os.path.abspath(self.filename)):
+            # print("about to run pandoc")
+            run_pandoc(self.filename, self.html_file)
+            self.append_autorefresh()
+            try:
+                self.firefox.refresh()
+            except selenium.common.exceptions.WebDriverException:
+                print(
+                    "I'm quitting!! You probably suspended the computer, which"
+                    " seems to freak selenium out.  Just restart"
+                )
+                self.firefox.quit()
+                self.init_firefox()
+            print("and refreshed!")
+        else:
+            # print("saw a change in",os.path.normpath(os.path.abspath(event.src_path)))
+            # print("not",os.path.normpath(os.path.abspath(self.filename)))
+            pass
+
+    def append_autorefresh(self):
+        # print("about to add scripts")
+        with open(self.html_file, "r", encoding="utf-8") as fp:
+            all_data = fp.read()
+        all_data = all_data.replace(
+            "</head>",
+            """
+    <script id="MathJax-script" async src="MathJax-3.1.2/es5/tex-mml-chtml.js"></script>
+    <script>
+        // When the page is about to be unloaded, save the current scroll position
+        window.addEventListener('beforeunload', function() {
+            sessionStorage.setItem('scrollPosition', window.scrollY);
+        });
+
+        // When the page has loaded, scroll to the previous scroll position
+        window.addEventListener('load', function() {
+            var scrollPosition = sessionStorage.getItem('scrollPosition');
+            if (scrollPosition) {
+                window.scrollTo(0, scrollPosition);
+                sessionStorage.removeItem('scrollPosition');
+            }
+        });
+    </script>
+</head>
+    """,
+        )
+        with open(self.html_file, "w", encoding="utf-8") as fp:
+            fp.write(all_data)
+        # print("done adding")
+
+
+def watch(filename):
+    observer = Observer()
+    event_handler = Handler(filename, observer)
+    observer.schedule(event_handler, path=".", recursive=False)
+    observer.start()
+
+    try:
+        while True:
+            time.sleep(1)
+    except KeyboardInterrupt:
+        observer.stop()
+
+    observer.join()
+    # print("returning from watch")
+
+
+if __name__ == "__main__":
+    filename = sys.argv[1]
+    watch(filename)
+    # Open the HTML file in the default web browser

pydifftools/copy_files.py

@@ -0,0 +1,75 @@
+# from https://tex.stackexchange.com/questions/24542/create-list-of-all-external-files-used-by-master-latex-document
+"""Copy figures used by document."""
+import os
+import shutil
+from pathlib import Path, PurePosixPath
+import subprocess
+import sys
+
+
+def copy_image_files(ROOT_TEX, project_name, TARGET_DIR, include_suppinfo):
+    all_files = []
+    with open(ROOT_TEX + ".tex", "r") as fp:
+        alltext = fp.read()
+    if r"\RequirePackage{snapshot}" not in alltext:
+        raise RuntimeError(
+            "You haven't called \\RequirePackage{snapshot} in the root tex file.  I can't do my thing without that!"
+        )
+    with open(ROOT_TEX + ".dep", "r") as f:
+        for line in f:
+            if "*{file}" in line:
+                value = line.split("{")[2].split("}")
+                source = value[0]
+                _, e = os.path.splitext(source)
+                if len(e) == 0 and os.path.exists(source + ".tex"):
+                    all_files.append(source + ".tex")
+                    print("found", source + ".tex")
+                elif os.path.exists(source):
+                    all_files.append(source)
+            elif "*{package}" in line:
+                value = line.split("{")[2].split("}")
+                source = value[0]
+                _, e = os.path.splitext(source)
+                if len(e) == 0 and os.path.exists(source + ".sty"):
+                    all_files.append(source + ".sty")
+                    print("found", source + ".sty")
+                elif os.path.exists(source):
+                    all_files.append(source)
+            else:
+                continue
+    os.makedirs(TARGET_DIR, exist_ok=True)
+    if include_suppinfo:
+        all_files.append("suppinfo.pdf")
+        all_files.append("suppinfo.aux")
+    for source in all_files:
+        d, f = os.path.split(source)
+        b, _ = os.path.splitext(source)
+        if b == ROOT_TEX:
+            f = f.replace(ROOT_TEX, "ms")
+        newpath = TARGET_DIR / d / f
+        print("copying", source, PurePosixPath(newpath))
+        if len(d) > 0:
+            print("going to make", newpath.parents[0])
+            os.makedirs(newpath.parents[0], exist_ok=True)
+        shutil.copy(source, PurePosixPath(newpath))
+    shutil.copy(ROOT_TEX + ".tex", os.path.join(TARGET_DIR, "ms.tex"))
+
+
+if __name__ == "__main__":
+    copy_image_files()
+    os.chdir(Path.cwd().parent)
+    output_filename = f"{project_name}_forarxiv.tgz"
+    # create tar process
+    tar = subprocess.Popen(
+        ["tar", "cf", "-", TARGET_DIR.name], stdout=subprocess.PIPE
+    )
+    # create gzip process, using tar's stdout as its stdin
+    gzip = subprocess.Popen(
+        ["gzip", "-9"], stdin=tar.stdout, stdout=subprocess.PIPE
+    )
+    # close tar's stdout so it doesn't hang around waiting for input
+    tar.stdout.close()
+    # write gzip's stdout to a file
+    with open(output_filename, "wb") as fp:
+        shutil.copyfileobj(gzip.stdout, fp)
+    gzip.stdout.close()

pydifftools/diff-doc.js

@@ -0,0 +1,193 @@
+//
+// TortoiseSVN Diff script for Word Doc files
+//
+// Copyright (C) 2004-2008 the TortoiseSVN team
+// This file is distributed under the same license as TortoiseSVN
+//
+// Last commit by:
+// $Author$
+// $Date$
+// $Rev$
+//
+// Authors:
+// Jared Silva, 2008
+// Davide Orlandi and Hans-Emil Skogh, 2005
+//
+
+var objArgs,num,sBaseDoc,sNewDoc,sTempDoc,objScript,word,destination;
+// Microsoft Office versions for Microsoft Windows OS
+var vOffice2000 = 9;
+var vOffice2002 = 10;
+var vOffice2003 = 11;
+var vOffice2007 = 12;
+// WdCompareTarget
+var wdCompareTargetSelected = 0;
+var wdCompareTargetCurrent = 1;
+var wdCompareTargetNew = 2;
+// WdViewType
+var wdMasterView = 5;
+var wdNormalView = 1;
+var wdOutlineView = 2;
+// WdSaveOptions
+var wdDoNotSaveChanges = 0;
+var wdPromptToSaveChanges = -2;
+var wdSaveChanges = -1;
+
+objArgs = WScript.Arguments;
+num = objArgs.length;
+if (num < 2)
+{
+   WScript.Echo("Usage: [CScript | WScript] diff-doc.js base.doc new.doc");
+   WScript.Quit(1);
+}
+
+sBaseDoc = objArgs(0);
+sNewDoc = objArgs(1);
+
+objScript = new ActiveXObject("Scripting.FileSystemObject");
+if ( ! objScript.FileExists(sBaseDoc))
+{
+    WScript.Echo("File " + sBaseDoc + " does not exist.  Cannot compare the documents.");
+    WScript.Quit(1);
+}
+if ( ! objScript.FileExists(sNewDoc))
+{
+    WScript.Echo("File " + sNewDoc + " does not exist.  Cannot compare the documents.");
+    WScript.Quit(1);
+}
+
+try
+{
+   word = WScript.CreateObject("Word.Application");
+}
+catch(e)
+{
+	// before giving up, try with OpenOffice
+	try
+	{
+		var OO;
+		OO = WScript.CreateObject("com.sun.star.ServiceManager");
+	}
+	catch(e)
+	{
+		WScript.Echo("You must have Microsoft Word or OpenOffice installed to perform this operation.");
+		WScript.Quit(1);
+	}
+	// yes, OO is installed - do the diff with that one instead
+	var objFile = objScript.GetFile(sNewDoc);
+	if ((objFile.Attributes & 1)==1)
+	{
+		// reset the readonly attribute
+		objFile.Attributes = objFile.Attributes & (~1);
+	}
+	//Create the DesktopSet 
+	var objDesktop = OO.createInstance("com.sun.star.frame.Desktop");
+	var objUriTranslator = OO.createInstance("com.sun.star.uri.ExternalUriReferenceTranslator");
+	//Adjust the paths for OO
+	sBaseDoc = sBaseDoc.replace(/\\/g, "/");
+	sBaseDoc = sBaseDoc.replace(/:/g, "|");
+	sBaseDoc = sBaseDoc.replace(/ /g, "%20");
+	sBaseDoc="file:///" + sBaseDoc;
+	sBaseDoc=objUriTranslator.translateToInternal(sBaseDoc);
+	sNewDoc = sNewDoc.replace(/\\/g, "/");
+	sNewDoc = sNewDoc.replace(/:/g, "|");
+	sNewDoc = sNewDoc.replace(/ /g, "%20");
+	sNewDoc="file:///" + sNewDoc;
+	sNewDoc=objUriTranslator.translateToInternal(sNewDoc);
+
+	//Open the %base document
+	var oPropertyValue = new Array();
+	oPropertyValue[0] = OO.Bridge_GetStruct("com.sun.star.beans.PropertyValue");
+	oPropertyValue[0].Name = "ShowTrackedChanges";
+	oPropertyValue[0].Value = true;
+	var objDocument=objDesktop.loadComponentFromURL(sNewDoc,"_blank", 0, oPropertyValue);
+	
+	//Set the frame
+	var Frame = objDesktop.getCurrentFrame();
+	
+	var dispatcher=OO.CreateInstance("com.sun.star.frame.DispatchHelper");
+	
+	//Execute the comparison
+	dispatcher.executeDispatch(Frame, ".uno:ShowTrackedChanges", "", 0, oPropertyValue);
+	oPropertyValue[0].Name = "URL";
+	oPropertyValue[0].Value = sBaseDoc;
+	dispatcher.executeDispatch(Frame, ".uno:CompareDocuments", "", 0, oPropertyValue);
+	WScript.Quit(0);
+}
+
+if (parseInt(word.Version) >= vOffice2007)
+{
+	sTempDoc = sNewDoc;
+	sNewDoc = sBaseDoc;
+	sBaseDoc = sTempDoc;
+}
+
+objScript = null;
+
+word.visible = true;
+
+// Open the new document
+try
+{
+    destination = word.Documents.Open(sNewDoc, true, true);
+}
+catch(e)
+{
+    WScript.Echo("Error opening " + sNewDoc);
+    // Quit
+    WScript.Quit(1);
+}
+
+// If the Type property returns either wdOutlineView or wdMasterView and the Count property returns zero, the current document is an outline.
+if (((destination.ActiveWindow.View.Type == wdOutlineView) || (destination.ActiveWindow.View.Type == wdMasterView)) && (destination.Subdocuments.Count == 0))
+{
+    // Change the Type property of the current document to normal
+    destination.ActiveWindow.View.Type = wdNormalView;
+}
+
+// Compare to the base document
+if (parseInt(word.Version) <= vOffice2000)
+{
+    // Compare for Office 2000 and earlier
+    try
+    {
+        destination.Compare(sBaseDoc);
+    }
+    catch(e)
+    {
+        WScript.Echo("Error comparing " + sBaseDoc + " and " + sNewDoc);
+        // Quit
+        WScript.Quit(1);
+    }
+}
+else
+{
+    // Compare for Office XP (2002) and later
+    try
+    {
+        destination.Compare(sBaseDoc, "Comparison", wdCompareTargetNew, true, true);
+    }
+    catch(e)
+    {
+        WScript.Echo("Error comparing " + sBaseDoc + " and " + sNewDoc);
+        // Close the first document and quit
+        destination.Close(wdDoNotSaveChanges);
+        WScript.Quit(1);
+    }
+}
+    
+// Show the comparison result
+if (parseInt(word.Version) < vOffice2007)
+{
+	word.ActiveDocument.Windows(1).Visible = 1;
+}
+    
+// Mark the comparison document as saved to prevent the annoying
+// "Save as" dialog from appearing.
+word.ActiveDocument.Saved = 1;
+    
+// Close the first document
+if (parseInt(word.Version) >= vOffice2002)
+{
+    destination.Close(wdDoNotSaveChanges);
+}

pydifftools/doc_contents.py

@@ -0,0 +1,107 @@
+from collections import OrderedDict
+from fuzzywuzzy import process
+
+
+class doc_contents_class(object):
+    prefix = {
+        "section": "",
+        "subsection": "\t",
+        "subsubsection": 2 * "\t",
+        "paragraph": 3 * "\t",
+    }
+    inv_prefix = {v: k for k, v in prefix.items()}
+
+    def __init__(self):
+        self.contents = OrderedDict()
+        self.contents["header"] = ""
+        self.types = {}
+        self.types["header"] = "header"
+        self._reordering_started = False
+        self._aliases = {}
+
+    def start_sec(self, thistype, thistitle):
+        assert thistitle not in self.contents.keys(), (
+            "more than one section with the name:\n" + thistitle
+        )
+        self.contents[thistitle] = ""
+        self.types[thistitle] = thistype
+        print("added", thistitle)
+
+    def __setstate__(self, d):
+        "set the info from a pickle"
+        self.contents = d["contents"]
+        self.types = d["types"]
+        self._aliases = {} # doesn't exist, but still needed
+        self._reordering_started = False
+        return
+
+    def __getstate__(self):
+        "return info for a pickle"
+        return {
+            "contents": self.contents,
+            "types": self.types,
+        }
+
+    def __iadd__(self, value):
+        self.contents[next(reversed(self.contents))] += value
+        return self
+
+    def __str__(self):
+        if len(self._processed_titles) > 0:
+            raise ValueError("the following section"
+            " titles were not utilized -- this program is"
+            " for reordering, not dropping!:\n"+str(self._processed_titles))
+        retval = ""
+        for j in self.contents.keys():
+            if self.types[j] != "header":
+                new_name = j
+                if j in self._aliases.keys():
+                    new_name = self._aliases[j]
+                retval += f"\\{self.types[j]}{{{new_name}}}"
+            retval += f"{self.contents[j]}"
+        return retval
+
+    @property
+    def outline(self):
+        retval = []
+        for j in self.contents.keys():
+            if self.types[j] != "header":
+                thistitle = (self.prefix[self.types[j]] + "\t").join(j.split("\n"))
+                retval.append(self.prefix[self.types[j]] + "*\t" + thistitle)
+        self._reordering_started = False
+        return "\n".join(retval)
+
+    def outline_in_order(self, thisline):
+        if not self._reordering_started:
+            self._processed_titles = [j for j in self.contents.keys()
+                    if self.types[j] != 'header']
+            self._reordering_started = True
+        ilevel = 0
+        spacelevel = 0
+        hitmarker = False
+        for j, thischar in enumerate(thisline):
+            if not hitmarker:
+                if thischar == " ":
+                    spacelevel += 1
+                if spacelevel == 4 or thischar == "\t":
+                    ilevel += 1
+                    spacelevel = 0
+                elif thischar == "*":
+                    hitmarker = True
+            else:
+                assert thischar in [" ", "\t"]
+                title = thisline[j + 1 :]
+                break
+        if not hitmarker:
+            raise ValueError("somehow, there wasn't a * marker!")
+        if title not in self.contents.keys():
+            best_match, match_quality = process.extractOne(title, self.contents.keys())
+            yesorno = input(f"didn't find\n\t{title}\nin keys, maybe you want\n\t{best_match}\nsay y or n")
+            if yesorno == 'y':
+                self._aliases[best_match] = title # will be replaced later
+                title = best_match
+            else:
+                raise ValueError("problem with replacement")
+        self.contents.move_to_end(title)
+        self._processed_titles.remove(title)
+        self.types[title] = self.inv_prefix[ilevel * "\t"]

pydifftools/html_comments.py

@@ -0,0 +1,33 @@
+# again rerun
+from lxml import html, etree
+import os
+from pyspecdata.fornotebook import *
+from pyspecdata import *
+import re
+
+fp = open(sys.argv[1], "r")
+content = fp.read()
+fp.close()
+doc = html.fromstring(content)
+commentlabel_re = re.compile(r"\[([A-Z]+)([0-9])\]")
+comment_dict = {}
+# for j in doc.xpath('descendant::*[@style="mso-element:comment"]'):
+newlist = []
+thisbody = doc.find("body")
+print("I found the body", lsafen(thisbody))
+commentlist = etree.Element("div", style="mso-element:comment-list")
+for j in doc.xpath('//span[@style="mso-element:comment"]'):
+    # for j in doc.xpath('//span[@style="mso-element:comment"]'):
+    # print 'found span with style:\n\n',lsafen(html.tostring(j),wrap = 60)
+    # if j.attrib['style'] == 'mso-element:comment':
+    print("found span with style:\n\n", lsafen(j.attrib, wrap=60))
+    newlist.append(j)
+    j.drop_tree()
+    commentlist.append(j)
+thisbody.append(commentlist)
+# print lsafen(map(html.tostring,newlist),wrap = 60)
+newfile = re.sub(r"(.*)(\.htm.*)", r"\1_htmlcomm\2", sys.argv[1])
+fp = open(newfile, "w")
+content = html.tostring(doc)
+fp.write(content)
+fp.close()