google-ngrams 0.1.0__tar.gz → 0.1.1__tar.gz

{google_ngrams-0.1.0/google_ngrams.egg-info → google_ngrams-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: google_ngrams
-Version: 0.1.0
+Version: 0.1.1
 Summary: Fetch and analyze Google Ngram data for specified word forms.
 Author-email: David Brown <dwb2@andrew.cmu.edu>
 Maintainer-email: David Brown <dwb2@andrew.cmu.edu>
@@ -20,6 +20,7 @@ Requires-Dist: importlib-resources>=6.5
 Requires-Dist: matplotlib>=3.5
 Requires-Dist: polars>=1.17
 Requires-Dist: scipy>=1.15
+Requires-Dist: statsmodels>=0.14
 
 
 google_ngrams: Fetch and analyze Google Ngram data for specified word forms.
@@ -51,7 +52,7 @@ You can install the released version of google_ngrams from `PyPI <https://pypi.o
 
 .. code-block:: install-google_ngrams
 
-    pip install google_ngrams
+    pip install google-ngrams
 
 
 Usage

{google_ngrams-0.1.0 → google_ngrams-0.1.1}/README.rst

@@ -28,7 +28,7 @@ You can install the released version of google_ngrams from `PyPI <https://pypi.o
 
 .. code-block:: install-google_ngrams
 
-    pip install google_ngrams
+    pip install google-ngrams
 
 
 Usage

google_ngrams-0.1.1/_quarto/.gitignore

@@ -0,0 +1 @@
+/.quarto/

google_ngrams-0.1.1/_quarto/_extensions/machow/interlinks/.gitignore

@@ -0,0 +1,3 @@
+*.html
+*.pdf
+*_files/

google_ngrams-0.1.1/_quarto/_extensions/machow/interlinks/_extension.yml

@@ -0,0 +1,7 @@
+title: Interlinks
+author: Michael Chow
+version: 1.1.0
+quarto-required: ">=1.2.0"
+contributes:
+  filters:
+    - interlinks.lua

google_ngrams-0.1.1/_quarto/_extensions/machow/interlinks/interlinks.lua

@@ -0,0 +1,254 @@
+local function read_inv_text(filename)
+    -- read file
+    local file = io.open(filename, "r")
+    if file == nil then
+        return nil
+    end
+    local str = file:read("a")
+    file:close()
+
+
+    local project = str:match("# Project: (%S+)")
+    local version = str:match("# Version: (%S+)")
+
+    local data = {project = project, version = version, items = {}}
+
+    local ptn_data =
+        "^" ..
+        "(.-)%s+" ..        -- name
+        "([%S:]-):" ..      -- domain
+        "([%S]+)%s+" ..     -- role
+        "(%-?%d+)%s+" ..     -- priority
+        "(%S*)%s+" ..       -- uri
+        "(.-)\r?$"         -- dispname
+
+
+    -- Iterate through each line in the file content
+    for line in str:gmatch("[^\r\n]+") do
+        if not line:match("^#") then
+            -- Match each line against the pattern
+            local name, domain, role, priority, uri, dispName = line:match(ptn_data)
+
+            -- if name is nil, raise an error
+            if name == nil then
+                error("Error parsing line: " .. line)
+            end
+
+            data.items[#data.items + 1] = {
+                name = name,
+                domain = domain,
+                role = role,
+                priority = priority,
+                uri = uri,
+                dispName = dispName
+            }
+        end
+    end
+    return data
+end
+
+local function read_json(filename)
+
+    local file = io.open(filename, "r")
+    if file == nil then
+        return nil
+    end
+    local str = file:read("a")
+    file:close()
+
+    local decoded = quarto.json.decode(str)
+    return decoded
+end
+
+local function read_inv_text_or_json(base_name)
+    local file = io.open(base_name .. ".txt", "r")
+    if file then
+        -- TODO: refactors so we don't just close the file immediately
+        io.close(file)
+        json = read_inv_text(base_name .. ".txt")
+
+    else
+        json = read_json(base_name .. ".json")
+    end
+
+    return json
+end
+
+local inventory = {}
+
+local function lookup(search_object)
+
+    local results = {}
+    for _, inv in ipairs(inventory) do
+        for _, item in ipairs(inv.items) do
+            -- e.g. :external+<inv_name>:<domain>:<role>:`<name>`
+            if item.inv_name and item.inv_name ~= search_object.inv_name then
+                goto continue
+            end
+
+            if item.name ~= search_object.name then
+                goto continue
+            end
+
+            if search_object.role and item.role ~= search_object.role then
+                goto continue
+            end
+
+            if search_object.domain and item.domain ~= search_object.domain then
+                goto continue
+            else
+                if search_object.domain or item.domain == "py" then
+                  table.insert(results, item)
+                end
+
+                goto continue
+            end
+
+            ::continue::
+        end
+    end
+
+    if #results == 1 then
+        return results[1]
+    end
+    if #results > 1 then
+        quarto.log.warning("Found multiple matches for " .. search_object.name .. ", using the first match.")
+        return results[1]
+    end
+    if #results == 0 then
+        quarto.log.warning("Found no matches for object:\n", search_object)
+    end
+
+    return nil
+end
+
+local function mysplit (inputstr, sep)
+    if sep == nil then
+            sep = "%s"
+    end
+    local t={}
+    for str in string.gmatch(inputstr, "([^"..sep.."]+)") do
+            table.insert(t, str)
+    end
+    return t
+end
+
+local function normalize_role(role)
+    if role == "func" then
+        return "function"
+    end
+    return role
+end
+
+local function build_search_object(str)
+    local starts_with_colon = str:sub(1, 1) == ":"
+    local search = {}
+    if starts_with_colon then
+        local t = mysplit(str, ":")
+        if #t == 2 then
+            -- e.g. :py:func:`my_func`
+            search.role = normalize_role(t[1])
+            search.name = t[2]:match("%%60(.*)%%60")
+        elseif #t == 3 then
+            -- e.g. :py:func:`my_func`
+            search.domain = t[1]
+            search.role = normalize_role(t[2])
+            search.name = t[3]:match("%%60(.*)%%60")
+        elseif #t == 4 then
+            -- e.g. :ext+inv:py:func:`my_func`
+            search.external = true
+
+            search.inv_name = t[1]:match("external%+(.*)")
+            search.domain = t[2]
+            search.role = normalize_role(t[3])
+            search.name = t[4]:match("%%60(.*)%%60")
+        else
+            quarto.log.warning("couldn't parse this link: " .. str)
+            return {}
+        end
+    else
+        search.name = str:match("%%60(.*)%%60")
+    end
+
+    if search.name == nil then
+        quarto.log.warning("couldn't parse this link: " .. str)
+        return {}
+    end
+
+    if search.name:sub(1, 1) == "~" then
+        search.shortened = true
+        search.name = search.name:sub(2, -1)
+    end
+    return search
+end
+
+local function report_broken_link(link, search_object, replacement)
+    -- TODO: how to unescape html elements like [?
+    return pandoc.Code(pandoc.utils.stringify(link.content))
+end
+
+function Link(link)
+    -- do not process regular links ----
+    if not link.target:match("%%60") then
+        return link
+    end
+
+    -- lookup item ----
+    local search = build_search_object(link.target)
+    local item = lookup(search)
+
+    -- determine replacement, used if no link text specified ----
+    local original_text = pandoc.utils.stringify(link.content)
+    local replacement = search.name
+    if search.shortened then
+        local t = mysplit(search.name, ".")
+        replacement = t[#t]
+    end
+
+    -- set link text ----
+    if original_text == "" and replacement ~= nil then
+        link.content = pandoc.Code(replacement)
+    end
+
+    -- report broken links ----
+    if item == nil then
+        return report_broken_link(link, search)
+    end
+    link.target = item.uri:gsub("%$$", search.name)
+
+
+    return link
+end
+
+local function fixup_json(json, prefix)
+    for _, item in ipairs(json.items) do
+        item.uri = prefix .. item.uri
+    end
+    table.insert(inventory, json)
+end
+
+return {
+    {
+        Meta = function(meta)
+            local json
+            local prefix
+            if meta.interlinks and meta.interlinks.sources then
+                for k, v in pairs(meta.interlinks.sources) do
+                    local base_name = quarto.project.offset .. "/_inv/" .. k .. "_objects"
+                    json = read_inv_text_or_json(base_name)
+                    prefix = pandoc.utils.stringify(v.url)
+                    if json ~= nil then
+                        fixup_json(json, prefix)
+                    end
+                end
+            end
+            json = read_inv_text_or_json(quarto.project.offset .. "/objects")
+            if json ~= nil then
+                fixup_json(json, "/")
+            end
+        end
+    },
+    {
+        Link = Link
+    }
+}

google_ngrams-0.1.1/_quarto/_quarto.yml

@@ -0,0 +1,83 @@
+project:
+  type: website
+  output-dir: _site
+
+website:
+  title: "google_ngrams"
+  description: "Fetch and analyze Google Ngram data for specified word forms."
+  page-navigation: true
+  favicon: "favicon.ico"
+  navbar:
+    background: light
+    pinned: true
+    logo: logo.png
+    left:
+      - text: "Get started"
+        file: get-started.qmd
+      - text: "TimeSeries"
+        file: time-series.qmd
+      - text: "Reference"
+        file: reference/index.qmd
+      - text: Learn more
+        menu:
+          - text: "VNC Clustering for R"
+            href: https://cran.r-project.org/web/packages/pseudobibeR/index.html
+            target: _blank
+    right:
+      - icon: github
+        href: https://github.com/browndw/google_ngrams
+        aria-label: google_ngrams on GitHub
+  sidebar:
+    style: "floating"
+    collapse-level: 1
+    contents:
+      - section: Fetching Data
+        contents:
+          - text: "`google_ngram`"
+            href: reference/google_ngram.qmd
+      - section: Time Series
+        contents:
+          - text: "`timeviz_barplot`"
+            href: reference/timeviz_barplot.qmd
+          - text: "`timeviz_scatterplot`"
+            href: reference/timeviz_scatterplot.qmd
+          - text: "`timeviz_screeplot`"
+            href: reference/timeviz_screeplot.qmd
+          - text: "`timeviz_screeplot`"
+            href: reference/timeviz_screeplot.qmd
+          - text: "`timeviz_vnc`"
+            href: reference/timeviz_vnc.qmd
+          - text: "`cluster_summary`"
+            href: reference/cluster_summary.qmd
+
+bibliography: references.bib
+
+format:
+  html:
+    sidebar: false
+
+quartodoc:
+  title: Reference
+  package: google_ngrams
+  sections:
+    - title: google_ngrams fetch function
+      desc: "Read in Google n-gram data"
+      package: google_ngrams.ngrams
+      contents:
+        - google_ngram
+    - title: google_ngrams TimeSeries
+      desc: "Analyze time series data"
+      package: google_ngrams.TimeSeries
+      contents:
+        - timeviz_barplot
+        - timeviz_scatterplot
+        - timeviz_screeplot
+        - timeviz_screeplot
+        - timeviz_vnc
+        - cluster_summary
+
+filters:
+  - interlinks
+
+interlinks:
+  sources: {}