Merge remote-tracking branch 'origin/develop' into support-updating-raw-note-contents

.gitea/workflows/tests.yaml

@@ -9,8 +9,8 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v3
       - run: apt-get update && apt-get install -y python3-pip
-      - run: pip install --break-system-package -e .
-      - run: pip install --break-system-package pytest
+      - run: pip install -e .
+      - run: pip install pytest
       - run: pytest
 
   mypy:
@@ -19,8 +19,8 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v3
       - run: apt-get update && apt-get install -y python3-pip
-      - run: pip install --break-system-package -e .
-      - run: pip install --break-system-package mypy
+      - run: pip install -e .
+      - run: pip install mypy
       - run: mypy org_rw --check-untyped-defs
 
   style-formatting:
@@ -29,8 +29,8 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v3
       - run: apt-get update && apt-get install -y python3-pip
-      - run: pip install --break-system-package -e .
-      - run: pip install --break-system-package black
+      - run: pip install -e .
+      - run: pip install black
       - run: black --check .
 
   style-sorted-imports:
@@ -39,8 +39,8 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v3
       - run: apt-get update && apt-get install -y python3-pip
-      - run: pip install --break-system-package -e .
-      - run: pip install --break-system-package isort
+      - run: pip install -e .
+      - run: pip install isort
       - run: isort --profile black --check .
 
   stability-extra-test:
@@ -49,5 +49,5 @@ jobs:
     - name: Check out repository code
       uses: actions/checkout@v3
     - run: apt-get update && apt-get install -y git-core python3-pip
-    - run: pip install --break-system-package -e .
+    - run: pip install -e .
     - run: bash extra-tests/check_all.sh

README.org

@@ -7,12 +7,6 @@ A python library to parse, modify and save Org-mode files.
 - Modify these data and write it back to disk.
 - Keep the original structure intact (indentation, spaces, format, ...).
 
-** Principles
-- Avoid any dependency outside of Python's standard library.
-- Don't do anything outside of the scope of parsing/re-serializing Org-mode files.
-- *Modification of the original text if there's no change is considered a bug (see [[id:7363ba38-1662-4d3c-9e83-0999824975b7][Known issues]]).*
-- Data structures should be exposed as it's read on Emacs's org-mode or when in doubt as raw as possible.
-- Data in the objects should be modificable as a way to update the document itself. *Consider this a Object-oriented design.*
 ** Safety mechanism
 As this library is still in early development. Running it over files might
 produce unexpected changes on them. For this reason it's heavily recommended to
@@ -27,9 +21,6 @@ Also, see [[id:76e77f7f-c9e0-4c83-ad2f-39a5a8894a83][Known issues:Structure modi
 not properly stored and can trigger this safety mechanism on a false-positive.
 
 * Known issues
-:PROPERTIES:
-:ID:       7363ba38-1662-4d3c-9e83-0999824975b7
-:END:
 ** Structure modifications
 :PROPERTIES:
 :ID:       76e77f7f-c9e0-4c83-ad2f-39a5a8894a83

org_rw/dom.py

@@ -24,14 +24,6 @@ class ResultsDrawerNode(DrawerNode):
         return "<Results: {}>".format(len(self.children))
 
 
-class GenericDrawerNode(DrawerNode):
-    def __init__(self, drawer_name):
-        self.drawer_name = drawer_name
-
-    def __repr__(self):
-        return "<Drawer{}: {}>".format(self.drawer_name, len(self.children))
-
-
 class PropertyNode:
     def __init__(self, key, value):
         self.key = key
@@ -70,18 +62,12 @@ class TableSeparatorRow:
     def __init__(self, orig=None):
         self.orig = orig
 
-    def get_raw(self):
-        return get_raw_contents(self.orig)
-
 
 class TableRow:
     def __init__(self, cells, orig=None):
         self.cells = cells
         self.orig = orig
 
-    def get_raw(self):
-        return get_raw_contents(self.orig)
-
 
 class Text:
     def __init__(self, content):

org_rw/org_rw.py

@@ -122,7 +122,6 @@ NON_FINISHED_GROUPS = (
     dom.ListGroupNode,
     dom.ResultsDrawerNode,
     dom.PropertyDrawerNode,
-    dom.GenericDrawerNode,
 )
 FREE_GROUPS = (dom.CodeBlock,)
 
@@ -415,7 +414,6 @@ class Headline:
                 if (
                     isinstance(line, DelimiterLine)
                     and line.delimiter_type == DelimiterLineType.END_BLOCK
-                    and line.type_data.subtype == current_node.header.type_data.subtype
                 ):
 
                     start = current_node.header.linenum
@@ -638,13 +636,6 @@ class Headline:
                     assert current_node is None
                     current_node = dom.ResultsDrawerNode()
 
-                    # TODO: Allow indentation of these blocks inside others
-                    indentation_tree = [current_node]
-                    tree.append(current_node)
-                elif content.strip().startswith(":") and content.strip().endswith(":"):
-                    assert current_node is None
-                    current_node = dom.GenericDrawerNode(content.strip().strip(":"))
-
                     # TODO: Allow indentation of these blocks inside others
                     indentation_tree = [current_node]
                     tree.append(current_node)
@@ -873,24 +864,9 @@ class Headline:
                 yield from get_links_from_content(item.content)
 
     def get_lines_between(self, start, end):
-        # @TODO: Generalize for other line types too.
-        everything = (
-            []
-            # + self.keywords
-            + self.contents
-            # + self.list_items
-            # + self.table_rows
-            # + self.properties
-            # + self.structural
-            + self.delimiters
-        )
-
-        for line in everything:
+        for line in self.contents:
             if start <= line.linenum < end:
-                if "get_raw" in dir(line):
-                    yield "".join(line.get_raw())
-                else:
-                    yield line.line
+                yield "".join(line.get_raw())
 
     def get_contents(self, format):
         if format == "raw":
@@ -901,6 +877,46 @@ class Headline:
         else:
             raise NotImplementedError()
 
+    def update_raw_contents(self, new_contents):
+        # Clear elements
+        self.keywords = []
+        self.contents = []
+        self.list_items = []
+        self.table_rows = []
+        self.properties = []
+        self.structural = []
+        self.delimiters = []
+        self.scheduled = None
+        self.deadline = None
+        self.closed = None
+
+        reader = OrgDocReader(environment=self.doc.environment)
+        reader.read(new_contents)
+
+        # No need to finalize as we can take the data from the reader instead of from a doc
+        if len(reader.headlines) > 0:
+            # Probably can be done by just adding the headlines to this one's children
+            raise NotImplementedError(
+                "new headlines on raw contents not supported yet. This probably should be simple, see comment on code."
+            )
+
+        for kw in reader.keywords:
+            self.keywords.append(offset_linenum(self.start_line + 1, kw))
+
+        for content in reader.contents:
+            self.contents.append(offset_linenum(self.start_line + 1, content))
+
+        for list_item in reader.list_items:
+            self.list_items.append(offset_linenum(self.start_line + 1, list_item))
+
+        for struct_item in reader.structural:
+            self.structural.append(offset_linenum(self.start_line + 1, struct_item))
+
+        for prop in reader.properties:
+            self.properties.append(offset_linenum(self.start_line + 1, prop))
+
+        # Environment is not used, as it's known
+
     def get_element_in_line(self, linenum):
         for line in self.contents:
             if linenum == line.linenum:
@@ -1098,6 +1114,7 @@ Keyword = collections.namedtuple(
 Property = collections.namedtuple(
     "Property", ("linenum", "match", "key", "value", "options")
 )
+Structural = collections.namedtuple("Structural", ("linenum", "line"))
 
 
 class ListItem:
@@ -1146,6 +1163,19 @@ TableRow = collections.namedtuple(
     ),
 )
 
+ItemWithLineNum = Union[Keyword, RawLine, Property, ListItem, Structural]
+
+
+def offset_linenum(offset: int, item: ItemWithLineNum) -> ItemWithLineNum:
+    if isinstance(item, ListItem):
+        item.linenum += offset
+        return item
+
+    assert isinstance(
+        item, (Keyword, RawLine, Property, Structural)
+    ), "Expected (Keyword|RawLine|Property|Structural), found {}".format(item)
+    return item._replace(linenum=item.linenum + offset)
+
 
 # @TODO How are [YYYY-MM-DD HH:mm--HH:mm] and ([... HH:mm]--[... HH:mm]) differentiated ?
 # @TODO Consider recurrence annotations
@@ -2331,7 +2361,6 @@ class OrgDoc:
         list_items,
         structural,
         properties,
-        delimiters,
         environment=BASE_ENVIRONMENT,
     ):
         self.todo_keywords = [HeadlineState(name=kw) for kw in DEFAULT_TODO_KEYWORDS]
@@ -2361,11 +2390,11 @@ class OrgDoc:
         self.list_items: List[ListItem] = list_items
         self.structural: List = structural
         self.properties: List = properties
-        self.delimiters: List = delimiters
         self._path = None
         self.headlines: List[Headline] = list(
             map(lambda hl: parse_headline(hl, self, self), headlines)
         )
+        self.environment = environment
 
     @property
     def id(self):
@@ -2526,9 +2555,6 @@ class OrgDoc:
         for struct in self.structural:
             lines.append(dump_structural(struct))
 
-        for content in self.delimiters:
-            lines.append(dump_delimiters(content))
-
         for kw in self.keywords:
             lines.append(dump_kw(kw))
 
@@ -2553,8 +2579,8 @@ class OrgDocReader:
         self.delimiters: List[DelimiterLine] = []
         self.list_items: List[ListItem] = []
         self.table_rows: List[TableRow] = []
-        self.structural: List = []
-        self.properties: List = []
+        self.structural: List[Structural] = []
+        self.properties: List[Property] = []
         self.current_drawer: Optional[List] = None
         self.environment = environment
 
@@ -2566,7 +2592,6 @@ class OrgDocReader:
             self.list_items,
             self.structural,
             self.properties,
-            self.delimiters,
             self.environment,
         )
 
@@ -2737,7 +2762,7 @@ class OrgDocReader:
     def add_property_drawer_line(self, linenum: int, line: str, match: re.Match):
         if len(self.headline_hierarchy) == 0:
             self.current_drawer = self.properties
-            self.structural.append((linenum, line))
+            self.structural.append(Structural(linenum, line))
         else:
             assert self.headline_hierarchy[-1] is not None
             self.current_drawer = self.headline_hierarchy[-1]["properties"]
@@ -2756,7 +2781,7 @@ class OrgDocReader:
     def add_drawer_end_line(self, linenum: int, line: str, match: re.Match):
         self.current_drawer = None
         if len(self.headline_hierarchy) == 0:
-            self.structural.append((linenum, line))
+            self.structural.append(Structural(linenum, line))
         else:
             assert self.headline_hierarchy[-1] is not None
             self.headline_hierarchy[-1]["structural"].append((linenum, line))

org_rw/utils.py

@@ -9,7 +9,6 @@ from .org_rw import (
     ListItem,
     RawLine,
     Strike,
-    TableRow,
     Text,
     Underlined,
     Verbatim,
@@ -51,8 +50,6 @@ def get_raw_contents(doc) -> str:
         return doc.get_raw()
     if isinstance(doc, ListItem):
         return dump_contents(doc)[1]
-    if isinstance(doc, TableRow):
-        return dump_contents(doc)[1]
     print("Unhandled type: " + str(doc))
     raise NotImplementedError("Unhandled type: " + str(doc))
 

requirements.txt

@@ -0,0 +1 @@
+# No external requirements at this point

tests/13-update-reparse-test.org

@@ -0,0 +1,22 @@
+#+TITLE: 13-Update reparse
+#+DESCRIPTION: Update-Reparse org file
+#+TODO: TODO(t) PAUSED(p) |  DONE(d)
+
+
+* First level
+  :PROPERTIES:
+  :ID:       13-update-reparse-first-level-id
+  :CREATED:  [2020-01-01 Wed 01:01]
+  :END:
+  First level content
+
+  - A list of items ::
+    - With a sublist
+
+  Something after the list.
+
+** Second level
+   :PROPERTIES:
+   :ID:       13-update-reparse-second-level-id
+   :END:
+   Second level content

tests/test_org.py

@@ -1,4 +1,5 @@
 import os
+import tempfile
 import unittest
 from datetime import datetime as DT
 
@@ -869,6 +870,86 @@ class TestSerde(unittest.TestCase):
 
         self.assertEqual(dumps(doc), orig)
 
+    def test_update_reparse_same_structure(self):
+        with open(os.path.join(DIR, "01-simple.org")) as f:
+            doc = load(f)
+
+        hl = doc.getTopHeadlines()[0]
+        ex = HL(
+            "First level",
+            props=[
+                ("ID", "01-simple-first-level-id"),
+                ("CREATED", DT(2020, 1, 1, 1, 1)),
+            ],
+            content="  First level content\n",
+            children=[
+                HL(
+                    "Second level",
+                    props=[("ID", "01-simple-second-level-id")],
+                    content="\n   Second level content\n",
+                    children=[
+                        HL(
+                            "Third level",
+                            props=[("ID", "01-simple-third-level-id")],
+                            content="\n    Third level content\n",
+                        )
+                    ],
+                )
+            ],
+        )
+
+        # Ground check
+        ex.assert_matches(self, hl)
+
+        # Update
+        lines = list(doc.dump_headline(hl, recursive=False))
+        assert lines[0].startswith("* ")  # Title, skip it
+        content = "\n".join(lines[1:])
+        hl.update_raw_contents(content)
+
+        # Check after update
+        ex.assert_matches(self, hl, accept_trailing_whitespace_changes=True)
+
+    def test_update_reparse_same_values(self):
+        with open(os.path.join(DIR, "13-update-reparse-test.org")) as f:
+            doc = load(f)
+
+        expected_hl_contents = """  :PROPERTIES:
+  :ID:       13-update-reparse-first-level-id
+  :CREATED:  [2020-01-01 Wed 01:01]
+  :END:
+  First level content
+
+  - A list of items ::
+    - With a sublist
+
+  Something after the list.
+"""
+
+        hl = doc.getTopHeadlines()[0]
+        lines = list(doc.dump_headline(hl, recursive=False))
+        assert lines[0].startswith("* ")  # Title, skip it
+        content = "\n".join(lines[1:])
+        self.assertEqual(content, expected_hl_contents)
+
+        # Check after update
+        hl.update_raw_contents(content)
+        self.assertEqual(content, expected_hl_contents)
+
+        # Check after dump and reload
+        with tempfile.NamedTemporaryFile("wt") as f:
+            save = org_rw.dumps(doc)
+            f.write(save)
+            f.flush()
+
+            with open(f.name, "rt") as reader:
+                reloaded = org_rw.load(reader)
+                re_hl = reloaded.getTopHeadlines()[0]
+                lines = list(doc.dump_headline(hl, recursive=False))
+                assert lines[0].startswith("* ")  # Title, skip it
+                content = "\n".join(lines[1:])
+                self.assertEqual(content, expected_hl_contents)
+
     def test_mimic_write_file_13(self):
         with open(os.path.join(DIR, "13-tags.org")) as f:
             orig = f.read()

tests/utils/assertions.py

@@ -67,7 +67,12 @@ class HL:
         self.content = content
         self.children = children
 
-    def assert_matches(self, test_case: unittest.TestCase, doc):
+    def assert_matches(
+        self,
+        test_case: unittest.TestCase,
+        doc,
+        accept_trailing_whitespace_changes=False,
+    ):
         test_case.assertEqual(self.title, get_raw(doc.title))
 
         # Check properties
@@ -84,7 +89,12 @@ class HL:
                         timestamp_to_datetime(doc_props[i].value), prop[1]
                     )
 
-        test_case.assertEqual(get_raw_contents(doc), self.get_raw())
+        if accept_trailing_whitespace_changes:
+            test_case.assertEqual(
+                get_raw_contents(doc).rstrip(), self.get_raw().rstrip()
+            )
+        else:
+            test_case.assertEqual(get_raw_contents(doc), self.get_raw())
 
         # Check children
         if self.children is None: