Change implementation of `_node_is_proof_immediately_following_a_theo…

…rem_like_environment` and `_node_is_nonspecial_following_a_sectionlike_node` in `29_latex.divide.ipynb` to not repeatedly use `get_node_from_simple_text`, which is time consuming
hyunjongkimmath · May 12, 2024 · 8337cfc · 8337cfc
1 parent 7557e9d
commit 8337cfc
Show file tree

Hide file tree

Showing 30 changed files with 3,063 additions and 83 deletions.
diff --git a/nbs/16_latex.convert.ipynb b/nbs/16_latex.convert.ipynb
@@ -597,7 +597,7 @@
      "output_type": "stream",
      "text": [
       "The following are the subdirectories of `reference_folder` (relative to `temp_vault`):\n",
-      "['.', '.obsidian', '.obsidian\\\\plugins', '.obsidian\\\\plugins\\\\fast-link-edit', '.obsidian\\\\plugins\\\\obsidian-vimrc-support', '.obsidian\\\\plugins\\\\trouver_obs', '1_proof_of_theorem~refthmain', '1_proof_of_theorem~refthmain\\\\11_this_is_a_subsection', '1_proof_of_theorem~refthmain\\\\12_this_is_another_subsection', 'test_ref_untitled_section', '_temp']\n"
+      "['.', '.obsidian', '.obsidian\\\\plugins', '.obsidian\\\\plugins\\\\fast-link-edit', '.obsidian\\\\plugins\\\\obsidian-vimrc-support', '1_proof_of_theorem~refthmain', '1_proof_of_theorem~refthmain\\\\11_this_is_a_subsection', '1_proof_of_theorem~refthmain\\\\12_this_is_another_subsection', 'test_ref_untitled_section', '_temp']\n"
      ]
     }
    ],
@@ -639,8 +639,8 @@
     "#| hide\n",
     "#| notest\n",
     "VaultNote.clear_cache()\n",
-    "reference = 'bruinier_yang_fhCMcdLf'\n",
-    "latex_file = Path(r'C:\\Users\\hyunj\\Documents\\Math\\latex_image_data\\latex_full') / reference / 'arxiv.tex'\n",
+    "reference = 'voevodsky_A1'\n",
+    "latex_file = Path(r'C:\\Users\\hyunj\\Documents\\Math\\latex_image_data\\latex_full') / reference / 'main.tex'\n",
     "\n",
     "# reference = 'numbering_example_1_consecutive_numbering_scheme'\n",
     "# latex_file = Path(r'C:\\Users\\hyunj\\Documents\\Development\\Python\\trouver\\nbs\\_tests\\latex_examples') / reference / 'main.tex'\n",
@@ -653,15 +653,15 @@
     "\n",
     "\n",
     "location = Path('.')  # The path relative to the vault of the directory in which to make the new folder containing the new notes.\n",
-    "author_names = ['Arinkin', 'Gaitsgory']\n",
+    "author_names = ['Voevodsky']\n",
     "\n",
     "setup_reference_from_latex_parts(\n",
     "    parts, cust_comms, vault, location,\n",
     "    reference,\n",
     "    author_names,\n",
     "    overwrite='w',\n",
     "    confirm_overwrite=True,\n",
-    "    adjust_common_latex_syntax_to_markdown=True,   # For things like adding `$$` around `\\begin{align*}...\\end{align*}`\n",
+    "    adjust_common_latex_syntax_to_markdown=False,   # For things like adding `$$` around `\\begin{align*}...\\end{align*}`\n",
     "    repeat_replacing_custom_commands=-1\n",
     "    )"
    ]
@@ -676,7 +676,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Identified reference 'poonen_arec' in the vault 'c:\\Users\\hyunj\\Documents\\Development\\Python\\trouver\\nbs\\_tests\\test_vault_5' as the folder 'c:\\Users\\hyunj\\Documents\\Development\\Python\\trouver\\nbs\\_tests\\test_vault_5\\poonen_arec'...\n",
+      "Identified reference 'voevodsky_A1' in the vault 'c:\\Users\\hyunj\\Documents\\Development\\Python\\trouver\\nbs\\_tests\\test_vault_5' as the folder 'c:\\Users\\hyunj\\Documents\\Development\\Python\\trouver\\nbs\\_tests\\test_vault_5\\voevodsky_A1'...\n",
       "Deleting...\n",
       "Deleted reference.\n",
       "\n"

diff --git a/nbs/29_latex.divide.ipynb b/nbs/29_latex.divide.ipynb
@@ -107,7 +107,20 @@
     "    r'\\{((?>[^{}]+|\\{(?2)\\})*)\\}'\n",
     "    r'\\s*'\n",
     "    r'(\\[\\s*(\\w+)\\s*\\])?',\n",
-    "    regex.MULTILINE)\n"
+    "    regex.MULTILINE)\n",
+    "\n",
+    "# matches \\section{title}, \\subsection{title}, \\subsubsection{title}, \\section*{title}, etc.\n",
+    "SECTION_LIKE_PATTERN = regex.compile(\n",
+    "        r'\\\\(?:section|subsection|subsubsection)\\s*(?:\\[.*\\])?(\\*)?\\s*'\n",
+    "        r'\\{((?>[^{}]+|\\{(?2)\\})*)\\}',\n",
+    "        regex.MULTILINE)\n",
+    "    \n",
+    "\n",
+    "# matches \\begin{theorem},\n",
+    "ENVIRONMENT_PATTERN = regex.compile(\n",
+    "        r'\\\\begin\\s*'\n",
+    "        r'\\{((?>[^{}]+|\\{(?1)\\})*)\\}',\n",
+    "        regex.MULTILINE)\n"
    ]
   },
   {
@@ -1658,12 +1671,12 @@
     "    # Note that the `section` command has the optional argument `toc-title` which appears\n",
     "    # in the table of contents, cf.\n",
     "    # http://latexref.xyz/_005csection.html\n",
-    "    pattern = regex.compile(\n",
-    "        r'\\\\(?:section|subsection|subsubsection)\\s*(?:\\[.*\\])?(\\*)?\\s*'\n",
-    "        r'\\{((?>[^{}]+|\\{(?2)\\})*)\\}',\n",
-    "        regex.MULTILINE\n",
-    "    )\n",
-    "    regex_search = regex.search(pattern, text)\n",
+    "    # pattern = regex.compile(\n",
+    "    #     r'\\\\(?:section|subsection|subsubsection)\\s*(?:\\[.*\\])?(\\*)?\\s*'\n",
+    "    #     r'\\{((?>[^{}]+|\\{(?2)\\})*)\\}',\n",
+    "    #     regex.MULTILINE\n",
+    "    # )\n",
+    "    regex_search = regex.search(SECTION_LIKE_PATTERN, text)\n",
     "    is_numbered = regex_search.group(1) is None\n",
     "    title = regex_search.group(2)\n",
     "    return is_numbered, title\n"
@@ -1728,20 +1741,54 @@
    "outputs": [],
    "source": [
     "#| export\n",
-    "def _is_section_node(node):\n",
+    "def _is_section_node(node: LatexNode):\n",
     "    return (node.isNodeType(LatexMacroNode)\n",
     "            and node.macroname == 'section')\n",
     "\n",
-    "def _is_subsection_node(node):\n",
+    "def _is_subsection_node(node: LatexNode):\n",
     "    return (node.isNodeType(LatexMacroNode)\n",
     "            and node.macroname == 'subsection')\n",
     "\n",
-    "def _is_subsubsection_node(node):\n",
+    "def _is_subsubsection_node(node: LatexNode):\n",
     "    return (node.isNodeType(LatexMacroNode)\n",
     "            and node.macroname == 'subsubsection')\n",
     "\n",
-    "def _is_environment_node(node):\n",
-    "    return node.isNodeType(LatexEnvironmentNode)"
+    "def _is_environment_node(node: LatexNode):\n",
+    "    return node.isNodeType(LatexEnvironmentNode)\n",
+    "\n",
+    "def _text_is_of_section_like_node(text: str):\n",
+    "    \"\"\"Return `True` if `text` represents the text for a section node.\n",
+    "\n",
+    "    In principal, this function should act like \n",
+    "    `_is_section_node or _is_subsection_node or _is_subsubsection_node`\n",
+    "    except that it takes a `str` as its argument instead of a `LatexNode`.\n",
+    "    This function is\n",
+    "    implemented using a regex pattern instead of using\n",
+    "    `_is_section_node` to save time.\n",
+    "    \"\"\"\n",
+    "    return bool(regex.match(SECTION_LIKE_PATTERN, text.lstrip()))\n",
+    "\n",
+    "\n",
+    "def _text_is_of_environment_node(text: str):\n",
+    "    \"\"\"Return `True` if `text` represents an environment node\n",
+    "    (at least at the start).\n",
+    "    \n",
+    "    In principal, this function should act like `_is_environment_node`\n",
+    "    except that it takes a `str` as its argument instead of a `LatexNode`.\n",
+    "    This function is implemented using a regex pattern instead of using\n",
+    "    '_is_environment_node` to save time.\n",
+    "    \"\"\"\n",
+    "    return bool(regex.match(ENVIRONMENT_PATTERN, text.lstrip()))\n",
+    "\n",
+    "\n",
+    "def _environment_name_of_text(text: str):\n",
+    "    \"\"\"Return `True` if `text` represents an environment node\n",
+    "    (at least at the start).\n",
+    "    \n",
+    "    Assumes that `_text_is_of_environment_node(text)` is `True`.\n",
+    "    \"\"\"\n",
+    "    match = regex.match(ENVIRONMENT_PATTERN, text.lstrip())\n",
+    "    return match.group(1)"
    ]
   },
   {
@@ -1790,6 +1837,45 @@
     "#         print(node.environmentname)\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'theorem'"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#| hide\n",
+    "assert _text_is_of_section_like_node(r\"\\section {Generating series of special divisors}\")\n",
+    "assert _text_is_of_section_like_node(r\"   \\section {Generating series of special divisors}\")\n",
+    "assert _text_is_of_section_like_node(r\"\\subsection{I am a subsection}\")\n",
+    "assert _text_is_of_section_like_node(r\"\\section*{I am an unnumbered section}\")\n",
+    "assert _text_is_of_section_like_node(r\"\\subsection*    {I am an unnumbered section and I have extraneous spaces}\")\n",
+    "assert _text_is_of_section_like_node(r\"\"\"\\section*    {I am a section and I have span \n",
+    "    multiple lines}\"\"\")\n",
+    "assert _text_is_of_section_like_node(r\"\"\"\\section{ Can I talk about the finite field \\mathcal{F}_p in this title?\n",
+    "        Can I also have multiple lines? Yes I can!}\"\"\")\n",
+    "assert _text_is_of_section_like_node(r\"\"\"\\subsubsection{Hi}\"\"\")\n",
+    "\n",
+    "assert not _text_is_of_section_like_node(r\"\"\"Something something\"\"\")\n",
+    "assert not _text_is_of_section_like_node(r\"\"\"\\begin{theorem}\"\"\")\n",
+    "assert not _text_is_of_section_like_node(r\"hi \\section{title}\")\n",
+    "\n",
+    "assert _text_is_of_environment_node(r\"\"\"\\begin{theorem} blah blah blah\"\"\")\n",
+    "assert _text_is_of_environment_node(r\"\"\"\\begin{theorem} blah blah blah \\end{theorem}\"\"\")\n",
+    "assert not _text_is_of_environment_node(r\"\"\"hi\"\"\")\n",
+    "_environment_name_of_text(r\"\"\"\\begin{theorem} blah blah blah\"\"\")\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -2759,10 +2845,13 @@
     "        return False\n",
     "    if accumulation.strip() != '':\n",
     "        return False\n",
-    "    previous_node = get_node_from_simple_text(parts[-1][1])\n",
-    "    if not _is_environment_node(previous_node):\n",
+    "    if not _text_is_of_environment_node(parts[-1][1]):\n",
     "        return False\n",
-    "    return previous_node.environmentname in display_names\n",
+    "    return _environment_name_of_text(parts[-1][1]) in display_names\n",
+    "    # previous_node = get_node_from_simple_text(parts[-1][1])\n",
+    "    # if not _is_environment_node(previous_node):\n",
+    "    #     return False\n",
+    "    # return previous_node.environmentname in display_names\n",
     "\n",
     "\n",
     "def _node_is_nonspecial_following_a_sectionlike_node(\n",
@@ -2773,18 +2862,18 @@
     "    \n",
     "    This is a helper function for `_process_node`.\n",
     "    \"\"\"\n",
-    "    # TODO: write tests\n",
     "    if ((_is_environment_node(node) and node.environmentname not in environments_to_not_divide_along)\n",
     "            or _is_section_node(node)\n",
     "            or _is_subsection_node(node)\n",
     "            or _is_subsubsection_node(node)):\n",
     "        return False\n",
-    "    if not len(parts) > 0:\n",
+    "    if len(parts) == 0:\n",
     "        return False\n",
     "    if accumulation.strip() != '':\n",
     "        return False\n",
-    "    previous_node = get_node_from_simple_text(parts[-1][1])\n",
-    "    return _is_section_node(previous_node) or _is_subsection_node(previous_node) or _is_subsubsection_node(previous_node)\n",
+    "    # previous_node = get_node_from_simple_text(parts[-1][1])\n",
+    "    # return _is_section_node(previous_node) or _is_subsection_node(previous_node) or _is_subsubsection_node(previous_node)\n",
+    "    return _text_is_of_section_like_node(parts[-1][1])\n",
     "    "
    ]
   },
@@ -2878,7 +2967,7 @@
     "DEFAULT_ENVIRONMENTS_TO_NOT_DIVIDE_ALONG = [\n",
     "    'align', 'align*', 'diagram', 'displaymath', 'displaymath*', 'enumerate', 'eqnarray', 'eqnarray*',\n",
     "    'equation', 'equation*', 'gather', 'gather*', 'itemize', 'label',\n",
-    "    'multiline', 'multiline*',\n",
+    "    'multiline', 'multiline*', 'multline', 'multline*',\n",
     "    'proof', 'quote', 'tabular', 'table', ]\n",
     "def divide_latex_text(\n",
     "        document: str, \n",
@@ -3334,6 +3423,8 @@
        " 'label',\n",
        " 'multiline',\n",
        " 'multiline*',\n",
+       " 'multline',\n",
+       " 'multline*',\n",
        " 'proof',\n",
        " 'quote',\n",
        " 'tabular',\n",
@@ -4181,13 +4272,6 @@
     "print(parts)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": null,

diff --git a/nbs/_tests/test_vault_5/.obsidian/workspace.json b/nbs/_tests/test_vault_5/.obsidian/workspace.json
@@ -4,11 +4,11 @@
     "type": "split",
     "children": [
       {
-        "id": "38ee778b7f30a004",
+        "id": "abee6198b82f053c",
         "type": "tabs",
         "children": [
           {
-            "id": "71dfae262b9a2adb",
+            "id": "ff13bff50f381407",
             "type": "leaf",
             "state": {
               "type": "empty",
@@ -69,8 +69,7 @@
               "state": {}
             }
           }
-        ],
-        "currentTab": 1
+        ]
       }
     ],
     "direction": "horizontal",
@@ -147,8 +146,21 @@
       "command-palette:Open command palette": false
     }
   },
-  "active": "71dfae262b9a2adb",
+  "active": "ff13bff50f381407",
   "lastOpenFiles": [
+    "voevodsky_A1/_temp/_index_temp_voevodsky_A1.md",
+    "voevodsky_A1/_temp",
+    "voevodsky_A1/_glossary_voevodsky_A1.md",
+    "voevodsky_A1/_notation_voevodsky_A1.md",
+    "voevodsky_A1/_template_voevodsky_A1_2.md",
+    "_templates/U-Z/V/_template_voevodsky_A1.md",
+    "_references/U-Z/V/_reference_voevodsky_A1.md",
+    "voevodsky_A1/voevodsky_a1_untitled_section/_index_voevodsky_a1_untitled_section.md",
+    "voevodsky_A1/_index_voevodsky_A1.md",
+    "voevodsky_A1/voevodsky_a1_untitled_section",
+    "voevodsky_A1",
+    "voevodsky_A1/voevodsky_a1_untitled_section/voevodsky_A1_abstract.md",
+    "_index.md",
     "bruinier_yang_fhCMcdLf/_index_bruinier_yang_fhCMcdLf.md",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/_index_7_height_pairings_on_modular_curves.md",
     "bruinier_yang_fhCMcdLf/8_the_case_n2/83_integral_model/bruinier_yang_fhCMcdLf_Theorem 8.2.md",
@@ -168,22 +180,9 @@
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_Theorem 7.20.md",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_Proposition 7.23.md",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_Lemma 7.24.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_Lemma 7.21.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_comment_50.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_comment_49.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_comment_48.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_7.4. Pull-back of Heegner divisors.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_64.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_63.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_62.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_61.md",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors/bruinier_yang_fhCMcdLf_60.md",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/74_pull_back_of_heegner_divisors",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/73_the_gross_zagier_formula",
     "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/72_the_shimura_lifting_and_hecke_eigenforms",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/71_the_modular_curve_x_0n",
-    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves",
-    "bruinier_yang_fhCMcdLf/6_the_n0_case",
-    "bruinier_yang_fhCMcdLf/5_faltings_heights_of_cm_cycles"
+    "bruinier_yang_fhCMcdLf/7_height_pairings_on_modular_curves/71_the_modular_curve_x_0n"
   ]
 }
diff --git a/nbs/_tests/test_vault_5/_references/U-Z/V/_reference_voevodsky_A1.md b/nbs/_tests/test_vault_5/_references/U-Z/V/_reference_voevodsky_A1.md
diff --git a/nbs/_tests/test_vault_5/_templates/U-Z/V/_template_voevodsky_A1.md b/nbs/_tests/test_vault_5/_templates/U-Z/V/_template_voevodsky_A1.md
@@ -0,0 +1,16 @@
+---
+cssclass: clean-embeds
+aliases: []
+tags: [_reference/voevodsky_A1, _meta/literature_note]
+---
+# Topic[^1]
+
+# See Also
+
+# Meta
+## References
+![[_reference_voevodsky_A1]]
+
+
+## Citations and Footnotes
+[^1]: Voevodsky, 
diff --git a/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/app.json b/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/app.json
@@ -0,0 +1,5 @@
+{
+  "vimMode": true,
+  "showLineNumber": true,
+  "livePreview": false
+}
diff --git a/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/appearance.json b/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/appearance.json
@@ -0,0 +1,4 @@
+{
+  "accentColor": "",
+  "theme": "obsidian"
+}
diff --git a/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/community-plugins.json b/nbs/_tests/test_vault_5/voevodsky_A1/.obsidian/community-plugins.json
@@ -0,0 +1,4 @@
+[
+  "trouver-obs",
+  "obsidian-vimrc-support"
+]