pyDiffTools 0.1.45__tar.gz → 0.1.47__tar.gz

{pydifftools-0.1.45/pyDiffTools.egg-info → pydifftools-0.1.47}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyDiffTools
-Version: 0.1.45
+Version: 0.1.47
 Summary: Diff tools
 Author: J M Franck
 License: Copyright (c) 2015, jmfranck

{pydifftools-0.1.45 → pydifftools-0.1.47/pyDiffTools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyDiffTools
-Version: 0.1.45
+Version: 0.1.47
 Summary: Diff tools
 Author: J M Franck
 License: Copyright (c) 2015, jmfranck

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/bibliography.py

@@ -64,9 +64,9 @@ class BibEntry:
         return f"@{self.kind}{{{key or self.key},\n{body}\n}}"
 
 
-def bib_entries(text):
-    """Index entry spans and raw fields without reserializing them."""
-    entries = {}
+def bib_entry_list(text):
+    """Every entry's span and raw fields in order, including repeated keys."""
+    entries = []
     position = 0
     while position < len(text):
         position = scan_bibtex(text, position, "@")
@@ -106,9 +106,17 @@ def bib_entries(text):
                 raise ValueError(f"duplicate BibTeX field {name} in {key}")
             fields[name] = body[offset:boundary].strip()
             offset = boundary + 1
-        if key in entries:
-            raise ValueError(f"duplicate BibTeX key {key}")
-        entries[key] = BibEntry(start, end + 1, kind, key, fields)
+        entries.append(BibEntry(start, end + 1, kind, key, fields))
+    return entries
+
+
+def bib_entries(text):
+    """Index entry spans and raw fields without reserializing them."""
+    entries = {}
+    for entry in bib_entry_list(text):
+        if entry.key in entries:
+            raise ValueError(f"duplicate BibTeX key {entry.key}")
+        entries[entry.key] = entry
     return entries
 
 
@@ -118,6 +126,8 @@ def normalized_text(value):
     return "".join(char for char in text if char.isalnum())
 
 
+# also used by: tests/test_bibliography.py, which checks these duplicate
+# rules directly (cpb calls it from zotero.recover_bibliography)
 def duplicate_reason(existing, incoming):
     """Identify likely duplicates for human review using Pandoc CSL records.
 
@@ -210,6 +220,8 @@ def markdown_ast(text, renames=None):
     return tree
 
 
+# also used by: tests/test_bibliography.py, which checks citation rewriting
+# directly (cpb calls it from zotero.recover_bibliography)
 def rewrite_citations(markdown, renames):
     """Replace citation tokens, accepting edits only when Pandoc confirms them.
 
@@ -241,6 +253,8 @@ def rewrite_citations(markdown, renames):
     return text.encode("utf-8")
 
 
+# also used by: tests/test_bibliography.py, which checks the all-or-nothing
+# replacement directly (cpb calls it from zotero.recover_bibliography)
 def replace_bibliography_files(changes):
     """Stage validated replacements and roll back if a later replacement fails.
 

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/browser_lifecycle.py

@@ -2,6 +2,17 @@ import os
 import shutil
 import subprocess
 
+# callbacks that run before any dialog needs the user; cpb registers one
+# that closes its live preview, so issues are dealt with before it reopens
+dialog_callbacks = []
+
+
+def prepare_for_dialog():
+    """Let watch commands close their preview before a dialog appears."""
+    for callback in list(dialog_callbacks):
+        callback()
+
+
 def browser_window_is_alive(browser):
     # Keep all browser liveness checks in one place so watch commands share
     # the same shutdown behavior when a user closes the browser window.
@@ -29,6 +40,8 @@ def close_browser_window(browser):
         pass
 
 
+# also used by: notebook/fast_build.py (qmdb's forward search), besides
+# cpb in continuous.py; tests/test_continuous_shutdown.py monkeypatches it
 def forward_search_in_browser(browser, search_text):
     # Reuse the same browser-side find logic across cpb and qmdb.
     if browser is None or not search_text:

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/citation_dialog.py

@@ -21,20 +21,49 @@ from PySide6.QtWidgets import (
 class DuplicateDialog(QDialog):
     """Choose an entry or merge fields; default to existing values and key."""
 
-    def __init__(self, matches, incoming, source):
+    def __init__(self, matches, incoming, source, mode="zotero"):
         super().__init__()
         self.matches = matches
         self.incoming = incoming
         self.decision = None
-        self.setWindowTitle("pydifft cpb — Possible duplicate citation")
         self.resize(1000, 650)
         layout = QVBoxLayout(self)
-        explanation = QLabel(
-            f"Review the imported citation for {source}.\n"
-            "Keeping or merging a duplicate also replaces @UNCHOSEN with "
-            "@CHOSEN in this Markdown file. Other documents are not edited.\n"
-            "For a merge, choose each field below, including the citation key."
-        )
+        if mode == "bibliography":
+            # {{{ two entries in the bibliography share one citation key
+            self.setWindowTitle("pydifft cpb — Duplicate citation key")
+            text = (
+                f"{source} defines @{incoming['key']} twice, so no missing "
+                "citations can be added until one entry is chosen.\n"
+                "Keep one entry, or merge them field by field; the other "
+                "entry is removed from the bibliography."
+            )
+            self.labels = ["First entry", "Second entry"]
+            actions = [
+                ("Keep first", "existing"),
+                ("Keep second", "incoming"),
+                ("Merge selected fields", "merge"),
+                ("Leave both (add no citations)", "skip"),
+            ]
+            # }}}
+        else:
+            self.setWindowTitle("pydifft cpb — Possible duplicate citation")
+            text = (
+                f"Review the imported citation for {source}.\n"
+                "Keeping or merging a duplicate also replaces @UNCHOSEN with "
+                "@CHOSEN in this Markdown file. Other documents are not "
+                "edited.\n"
+                "For a merge, choose each field below, including the citation "
+                "key."
+            )
+            self.labels = ["Existing", "Zotero"]
+            actions = [
+                ("Keep existing", "existing"),
+                ("Keep Zotero", "incoming"),
+                ("Merge selected fields", "merge"),
+                ("Not a duplicate: keep both", "both"),
+                ("Skip this import", "skip"),
+            ]
+        explanation = QLabel(text)
         explanation.setWordWrap(True)
         layout.addWidget(explanation)
         self.match_selector = QComboBox()
@@ -44,7 +73,16 @@ class DuplicateDialog(QDialog):
         self.table = QTableWidget()
         self.table.setColumnCount(4)
         self.table.setHorizontalHeaderLabels(
-            ["Field", "Existing bibliography", "Zotero", "Merge uses"]
+            [
+                "Field",
+                (
+                    "Existing bibliography"
+                    if mode == "zotero"
+                    else self.labels[0]
+                ),
+                self.labels[1],
+                "Merge uses",
+            ]
         )
         self.table.horizontalHeader().setSectionResizeMode(
             QHeaderView.ResizeMode.Stretch
@@ -52,13 +90,7 @@ class DuplicateDialog(QDialog):
         layout.addWidget(self.table)
         buttons = QHBoxLayout()
         self.buttons = {}
-        for label, action in [
-            ("Keep existing", "existing"),
-            ("Keep Zotero", "incoming"),
-            ("Merge selected fields", "merge"),
-            ("Not a duplicate: keep both", "both"),
-            ("Skip this import", "skip"),
-        ]:
+        for label, action in actions:
             button = QPushButton(label)
             button.setAutoDefault(False)
             button.clicked.connect(
@@ -94,9 +126,9 @@ class DuplicateDialog(QDialog):
                 self.table.setItem(row, column, cell)
             selector = QComboBox()
             if name in self.left:
-                selector.addItem("Existing", self.left[name])
+                selector.addItem(self.labels[0], self.left[name])
             if name in self.right:
-                selector.addItem("Zotero", self.right[name])
+                selector.addItem(self.labels[1], self.right[name])
             self.table.setCellWidget(row, 3, selector)
             self.selectors[name] = selector
         self.table.resizeRowsToContents()

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/comment_migration.py

@@ -11,6 +11,8 @@ import textwrap
 
 import yaml
 
+from .browser_lifecycle import prepare_for_dialog
+
 _FRONT_MATTER_RE = re.compile(
     r"\A(\ufeff?---[ \t]*\r?\n)(.*?)(\r?\n(?:---|\.\.\.)[ \t]*(?:\r?\n|$))",
     re.DOTALL,
@@ -78,6 +80,8 @@ def _most_distant_hue(colors):
     return (start + gap_size / 2) % 360
 
 
+# also used by: tests/test_comment_migration.py, which compiles its Qt
+# script and monkeypatches it (cpb calls it from prepare_comment_source)
 def _migration_dialog(filename, colors, legacy):
     """Ask Qt for all migrations and return decisions without editing files."""
     script = r"""
@@ -280,6 +284,7 @@ if result["accepted"]:
 
 print(json.dumps(result))
 """
+    prepare_for_dialog()
     completed = subprocess.run(
         # the dialog reads the document from its file, since the text of a
         # large document exceeds the operating system's argument limit

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/continuous.py

@@ -23,7 +23,9 @@ from .comment_migration import prepare_comment_source
 from .browser_lifecycle import (
     browser_window_is_alive,
     close_browser_window,
+    dialog_callbacks,
     forward_search_in_browser,
+    prepare_for_dialog,
 )
 from .forward_search import (
     CPB_FORWARD_SEARCH_PORT,
@@ -63,6 +65,9 @@ def _comment_filter_mode(path, packaged_filters=None):
 
 
 # Kept separate so its prompt choices can be unit-tested.
+# also used by: tests/test_wrap_check.py and tests/cli/test_commands.py,
+# which call it directly or monkeypatch it to answer the prompt (cpb calls
+# it from run_pandoc)
 def confirm_restore_comment_filter(active_mode):
     if active_mode == "none":
         message = (
@@ -112,6 +117,7 @@ if box.clickedButton() is restore_button:
     sys.exit(0)
 sys.exit(1)
 """
+    prepare_for_dialog()
     result = subprocess.run(
         [sys.executable, "-c", prompt_script, message, default_choice],
         capture_output=True,
@@ -127,6 +133,8 @@ sys.exit(1)
     raise RuntimeError("pydifft cpb filter dialog failed.")
 
 
+# also used by: tests/test_wrap_check.py, which drives this window directly
+# (cpb calls it from run_pandoc)
 def show_markdown_fix_dialog(report):
     """Show automatic fixes and any source edits that still need a user."""
     from html import escape
@@ -148,6 +156,7 @@ def show_markdown_fix_dialog(report):
     layout = report.get("layout", [])
     if not fixes and not warnings and not layout:
         return
+    prepare_for_dialog()
 
     # a QApplication must exist before any widget is constructed
     application = QApplication.instance() or QApplication([])
@@ -362,6 +371,8 @@ def show_markdown_fix_dialog(report):
     return user_says_fixed
 
 
+# also used by: tests/test_wrap_check.py, which drives this window directly
+# (cpb calls it from run_pandoc)
 def show_markdown_reload_dialog():
     """Ask the user to reload a source file changed by automatic fixes."""
     from PySide6.QtWidgets import (
@@ -372,6 +383,7 @@ def show_markdown_reload_dialog():
         QVBoxLayout,
     )
 
+    prepare_for_dialog()
     # a QApplication must exist before any widget is constructed
     application = QApplication.instance() or QApplication([])
     dialog = QDialog()
@@ -421,6 +433,10 @@ def run_pandoc(
         break
 
     if automatic_fixes_were_made:
+        # a corrected comment tag (e.g. <XYcomm> -> <XYcom>) can name an
+        # author with no XYcolor yet, so migrate comments again now rather
+        # than on the next save
+        prepare_comment_source(filename)
         show_markdown_reload_dialog()
     # }}}
 
@@ -909,7 +925,6 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
         daemon=True,
     )
     chrome = None
-    notice = None
     observer = None
     observer_started = False
     socket_thread_started = False
@@ -924,6 +939,9 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
         # orphaned browser session. Remember the source version from before
         # the build so an edit during a slow Pandoc run remains pending.
         source_missing = object()
+        # every dialog is dealt with (OK pressed) before Pandoc runs or
+        # Chrome opens
+        zotero_notice()
         prepare_comment_source(filename)
         initial_source_stat = os.stat(source_path)
         handled_signature = (
@@ -940,7 +958,6 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
             wrapnumber=wrapnumber,
         )
         append_autorefresh(html_file)
-        notice = zotero_notice()
 
         # Selenium is deliberately initialized once, after the first
         # successful build. Nothing in recovery constructs a browser.
@@ -992,6 +1009,16 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
         # immediately after Chrome loads can become polling's initial snapshot
         # and never be reported as a change.
         chrome.get("file://" + os.path.abspath(html_file))
+
+        def close_for_dialog():
+            # a rebuild needs the user, so close the preview while the
+            # issues are dealt with; it reopens once the rebuild is done
+            nonlocal chrome
+            if chrome is not None:
+                close_browser_window(chrome)
+                chrome = None
+
+        dialog_callbacks.append(close_for_dialog)
         rebuild_pending = False
         stable_signature = None
         stable_since = None
@@ -1102,18 +1129,26 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
                                 traceback.print_exc()
                         else:
                             handled_signature = attempted_signature
-                            if not browser_window_is_alive(chrome):
-                                break
-                            try:
-                                chrome.refresh()
-                            except WebDriverException:
-                                print(
-                                    "pydifft cpb: Chrome is no longer "
-                                    "available; stopping without reopening "
-                                    "it.",
-                                    file=sys.stderr,
-                                )
-                                break
+                            if chrome is not None:
+                                if not browser_window_is_alive(chrome):
+                                    break
+                                try:
+                                    chrome.refresh()
+                                except WebDriverException:
+                                    print(
+                                        "pydifft cpb: Chrome is no longer "
+                                        "available; stopping without "
+                                        "reopening it.",
+                                        file=sys.stderr,
+                                    )
+                                    break
+                        if chrome is None:
+                            # {{{ reopen the preview a dialog closed
+                            chrome = webdriver.Chrome()
+                            chrome.get(
+                                "file://" + os.path.abspath(html_file)
+                            )
+                            # }}}
             # }}}
             time.sleep(MAIN_LOOP_INTERVAL_SECONDS)
     except KeyboardInterrupt:
@@ -1127,10 +1162,7 @@ def cpb(filename, comments_to_margin=False, no_comments=False, wrapnumber=79):
         if socket_thread_started:
             socket_thread.join()
         close_browser_window(chrome)
-        if notice is not None:
-            if notice.poll() is None:
-                notice.terminate()
-            notice.wait()
+        dialog_callbacks.clear()
 
 
 if __name__ == "__main__":

{pydifftools-0.1.45 → pydifftools-0.1.47}/pydifftools/wrap_sentences.py

@@ -29,6 +29,11 @@ DETACHED_CROSSREF = re.compile(
     r"(?:(?<!\\)\$\$|\))(?P<gap>[ \t]*\n?[ \t]*)(?=\{#(?:eq|fig):)"
     r"|(?P<marker>\{#(?:eq|fig):[^}\n]*\n[^}]*\})"
 )
+# Comment tags are two initials and "com" (<JFcom>, <JFcom-left>, ...); the
+# comment filter passes a misspelling such as <JFcomm> through as raw HTML.
+MISSPELLED_COMMENT_TAG = re.compile(
+    r"<(/?)([A-Za-z]{2})comm(?:ent)?(-left|-right)?>", re.IGNORECASE
+)
 LATEX_MACRO_SPLIT = re.compile(
     r"(\\(?:begin|end|usepackage|newcommand|section"
     r"|subsection|subsubsection|paragraph|input){[^}]*})"
@@ -1055,18 +1060,29 @@ def markdown_lint_issues_from_text(
         (issue["line"], issue["message"])
         for issue in unclosed_markdown_spans(content)
     )
-    # {{{ report single trailing spaces and detached crossref markers
+    # {{{ report single trailing spaces, misspelled comment tags and
+    # detached crossref markers
     fence = None
     for number, line in enumerate(content.splitlines(), start=1):
         opening = re.match(r"[ \t]*(\x60{3,}|~{3,})", line)
         if opening and (fence is None or opening[1].startswith(fence)):
             fence = None if fence else opening[1]
-        elif fence is None and re.search(r"(?<! ) $", line):
+            continue
+        if fence is not None:
+            continue
+        if re.search(r"(?<! ) $", line):
             issues.append((
                 number,
                 "trailing space: remove the single space at the end of this "
                 "line (two spaces are a deliberate hard line break)",
             ))
+        misspelled = MISSPELLED_COMMENT_TAG.search(line)
+        if misspelled:
+            issues.append((
+                number,
+                f"misspelled comment tag: {misspelled[0]} should be "
+                f"<{misspelled[1]}{misspelled[2]}com{misspelled[3] or ''}>",
+            ))
     for found in DETACHED_CROSSREF.finditer(prose_content):
         if found["gap"] == "":
             continue
@@ -1207,8 +1223,8 @@ def apply_markdown_issue_fix(content, line_number, message):
             updated,
             before,
             after,
-            "A crossref marker was separated from its equation or figure. "
-            "I joined it back on.",
+            "One or more crossref markers were separated from their "
+            "equation or figure. I joined them back on.",
         )
         # }}}
     old_line = lines[index]
@@ -1233,13 +1249,28 @@ def apply_markdown_issue_fix(content, line_number, message):
     else:
         prefix = re.match(r"^[ \t]*", old_line).group()
     # }}}
+    if message.startswith("misspelled comment tag:"):
+        fixed = MISSPELLED_COMMENT_TAG.sub(
+            lambda found: f"<{found[1]}{found[2]}com{found[3] or ''}>",
+            old_line,
+        )
+        lines[index] = fixed + ending
+        return (
+            "".join(lines),
+            old_line,
+            fixed,
+            "One or more comment tags were misspelled, so they would not "
+            "show as comments. A comment tag is two initials and com, as in "
+            "&lt;JFcom&gt;. I corrected them.",
+        )
     if message.startswith("trailing space:"):
         lines[index] = old_line[:-1] + ending
         return (
             "".join(lines),
             old_line,
             old_line[:-1],
-            "A line ended with a single stray space. I removed it.",
+            "One or more lines ended with a single stray space. I removed "
+            "those spaces.",
         )
     if message.startswith("line too long:"):
         match = re.search(r"after '(.+?)' \(before '(.+?)'\); move", message)
@@ -1263,8 +1294,8 @@ def apply_markdown_issue_fix(content, line_number, message):
         first = old_line[:split_at].rstrip()
         second = old_line[split_at:].lstrip(" \t")
         reason = (
-            "This line was hard to read because it held too many words. "
-            "I moved the next words onto a new line."
+            "One or more lines were run-on lines, longer than the line "
+            "width. I moved the extra words onto new lines."
         )
     elif message.startswith("sentence ends mid-line"):
         boundary = SENTENCE_BOUNDARY.search(old_line)
@@ -1276,8 +1307,11 @@ def apply_markdown_issue_fix(content, line_number, message):
         first = old_line[: boundary.end(1)].rstrip()
         second = old_line[boundary.end(2) :].lstrip(" \t")
         reason = (
-            "A sentence ended, but the next sentence continued on the same "
-            "source line. I started it on a new line."
+            "One or more sentences started in the middle of a source line. "
+            "Since you can line-break the source wherever you want (only "
+            "double breaks give a new paragraph), you should <b>always "
+            "start sentences on new lines</b>. I started each one on a new "
+            "line."
         )
     else:
         raise ValueError(f"No automatic fix is available for {message!r}")
@@ -1614,15 +1648,15 @@ def autofix_markdown_file(
                 reasons = []
                 if result["linted"]:
                     reasons.append(
-                        "This edit made a line too long or ended a sentence "
-                        "mid-line. I broke it where it keeps the most lines "
-                        "unchanged from git HEAD."
+                        "One or more edits made a line too long or ended a "
+                        "sentence mid-line. I broke those lines where they "
+                        "keep the most lines unchanged from git HEAD."
                     )
                 if result["moved"]:
                     reasons.append(
-                        "This edit moved a line break away from where git "
-                        "HEAD has it. I put it back so the unchanged lines "
-                        "stay unchanged."
+                        "One or more edits moved a line break away from "
+                        "where git HEAD has it. I put those breaks back so "
+                        "the unchanged lines stay unchanged."
                     )
                 fixes.append(
                     {