docs-html-konwerter 0.1.0__tar.gz

docs_html_konwerter-0.1.0/PKG-INFO

@@ -0,0 +1,6 @@
+Metadata-Version: 2.4
+Name: docs-html-konwerter
+Version: 0.1.0
+Project-URL: Repository, https://github.com/stanislawbartkowski/docs-html-konwerter
+Requires-Python: >=3.10
+Requires-Dist: xml-konwerter

docs_html_konwerter-0.1.0/README.md

@@ -0,0 +1 @@
+# docs-html-konwerter

docs_html_konwerter-0.1.0/pyproject.toml

@@ -0,0 +1,17 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "docs-html-konwerter"
+version = "0.1.0"
+requires-python = ">=3.10"
+dependencies = [
+    "xml-konwerter",
+]
+
+[project.urls]
+Repository = "https://github.com/stanislawbartkowski/docs-html-konwerter"
+
+[tool.setuptools.packages.find]
+where = ["src"]

docs_html_konwerter-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

docs_html_konwerter-0.1.0/src/docs_html_konwerter/__init__.py

@@ -0,0 +1,5 @@
+from .doc_konwerter import parsehtml
+
+__all__ = [
+    "parsehtml",
+]

docs_html_konwerter-0.1.0/src/docs_html_konwerter/doc_konwerter.py

@@ -0,0 +1,85 @@
+import shutil
+import os
+import subprocess
+from tempfile import NamedTemporaryFile
+
+import xml.etree.ElementTree as et
+
+from xml_konwerter import konwertujdok
+
+_LINIE = ""
+_LINIE1 = "1"
+_LINIE2 = "2"
+_LINIE3 = "3"
+_LINIE4 = "4"
+_LINIETPOD = "TPOD"
+_LINIETNAD = "TNAD"
+
+_LISTA = "linie"
+_LISTA1 = "linie1"
+_LISTA2 = "linie2"
+_LISTA3 = "linie3"
+_LISTA4 = "linie4"
+_LISTATPOD = "linietpod"
+_LISTATNAD = "linietnad"
+
+_LI_CH = ["nbsp", "oacute", "hellip", "Oacute"]
+
+_htmlkeypairing = [
+    (_LINIE, _LISTA),
+    (_LINIE1, _LISTA1),
+    (_LINIE2, _LISTA2),
+    (_LINIE3, _LISTA3),
+    (_LINIE4, _LISTA4),
+    (_LINIETPOD, _LISTATPOD),
+    (_LINIETNAD, _LISTATNAD)
+]
+
+
+def _replace_ch(tname, ch):
+    command = ["sed", "-i", "-e", f's/\&{ch};/{ch};/g', tname]
+    subprocess.call(command)
+
+
+def _replace_ch_back(tname, ch):
+    command = ["sed", "-i", "-e", f's/{ch};/\&{ch};/g', tname]
+    subprocess.call(command)
+
+
+def _replace_tag(tname, tag):
+    pars = f's/<{tag}\([^>]*\)>/<{tag}\\1\\/>/g'
+    command = ["sed", "-i", "-e", pars, tname]
+    subprocess.call(command)
+
+
+def _replace_page_break(tname):
+    before = "page-break-before:always;display:none;"
+    after = "page-break-before:always;"
+    pars = f's/{before}/{after}/g'
+    command = ["sed", "-i", "-e", pars, tname]
+    subprocess.call(command)
+
+
+def _remove_meta(htmltemplate, tname):
+    shutil.copyfile(htmltemplate, tname)
+    _replace_tag(tname, "meta")
+    _replace_tag(tname, "img")
+    _replace_tag(tname, "hr")
+    _replace_page_break(tname)
+    for ch in _LI_CH:
+        _replace_ch(tname, ch)
+
+
+def _restore_nbsp(output):
+    for ch in _LI_CH:
+        _replace_ch_back(output, ch)
+
+
+def parsehtml(htmltemplate: str, outputdir: str, outputhtml: str, d: dict):
+    with NamedTemporaryFile() as tfile:
+        tname = tfile.name
+        _remove_meta(htmltemplate, tname)
+        htmloutputfile = os.path.join(outputdir, outputhtml)
+        konwertujdok(tname, htmloutputfile, d,
+                     htmlkeypairing=_htmlkeypairing)
+    _restore_nbsp(htmloutputfile)

docs_html_konwerter-0.1.0/src/docs_html_konwerter.egg-info/PKG-INFO

@@ -0,0 +1,6 @@
+Metadata-Version: 2.4
+Name: docs-html-konwerter
+Version: 0.1.0
+Project-URL: Repository, https://github.com/stanislawbartkowski/docs-html-konwerter
+Requires-Python: >=3.10
+Requires-Dist: xml-konwerter

docs_html_konwerter-0.1.0/src/docs_html_konwerter.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+src/docs_html_konwerter/__init__.py
+src/docs_html_konwerter/doc_konwerter.py
+src/docs_html_konwerter.egg-info/PKG-INFO
+src/docs_html_konwerter.egg-info/SOURCES.txt
+src/docs_html_konwerter.egg-info/dependency_links.txt
+src/docs_html_konwerter.egg-info/requires.txt
+src/docs_html_konwerter.egg-info/top_level.txt
+tests/test1.py

docs_html_konwerter-0.1.0/src/docs_html_konwerter.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

docs_html_konwerter-0.1.0/src/docs_html_konwerter.egg-info/requires.txt

@@ -0,0 +1 @@
+xml-konwerter

docs_html_konwerter-0.1.0/src/docs_html_konwerter.egg-info/top_level.txt

@@ -0,0 +1 @@
+docs_html_konwerter

docs_html_konwerter-0.1.0/tests/test1.py

@@ -0,0 +1,128 @@
+import os
+import unittest
+
+import helper as H
+
+from docs_html_konwerter import parsehtml
+
+
+_TESTDOKUMENT = "TestDokument1.html"
+_DOKUMENTPROSTEPOWT = "ProstePowtorz1.html"
+_TESTDOKUMENT2 = "TestDokument2.html"
+_TESTDOKUMENT3 = "TestDokument3.html"
+_TDOKUMENT = "TestDokumentTLinie.html"
+_HELLOPAGE = "TestHelloPage.html"
+
+
+class TestHtmlKonwerter(unittest.TestCase):
+
+    def _prosty_html(self, htmltemplate, lista=False):
+        htmlfile = H.html_file(htmltemplate)
+        print(htmlfile)
+        outputdir = H.tmpdir()
+        liniepod = [{"LPOD": f"To jest linia pod o numerz {no}"}
+                    for no in range(100)]
+        d = {
+            "IMIE": "Juliusz",
+            "NAZWISKO": "Cezar",
+            "linietpod": liniepod,
+            "linie": [
+                        {
+                            "NAZWA": "Artykuł",
+                            "KWOTA": "999 USD"
+                        }
+            ]
+
+        }
+        parsehtml(htmltemplate=htmlfile, outputdir=outputdir,
+                  outputhtml=htmltemplate, d=d)
+        outfile = os.path.join(outputdir, htmltemplate)
+        with open(outfile) as f:
+            xml = f.read()
+        print(xml)
+        self.assertIn("Juliusz", xml)
+        self.assertIn("Cezar", xml)
+        if lista:
+            self.assertIn("Artyku", xml)
+            self.assertIn("999 USD", xml)
+        return xml
+
+    def test_proste(self):
+        self._prosty_html(_TESTDOKUMENT)
+
+    def test_proste2(self):
+        self._prosty_html(_TESTDOKUMENT2, lista=True)
+
+    def test_proste3(self):
+        self._prosty_html(_TESTDOKUMENT3, lista=True)
+
+    def test_proste4(self):
+        xml = self._prosty_html(_TDOKUMENT, lista=True)
+        self.assertIn("To jest linia pod o numerz 99", xml)
+
+    def test_proste_linie(self):
+        htmlfile = H.html_file(_DOKUMENTPROSTEPOWT)
+        print(htmlfile)
+        outputdir = H.tmpdir()
+        d = {
+            "linie": [
+                {
+                    "IMIE": "Juliusz",
+                    "NAZWISKO": "Cezar",
+                    "linie": [
+                        {
+                            "NAZWA": "Artykuł",
+                            "KWOTA": "999 USD"
+                        }
+                    ]
+                }
+            ]
+        }
+        parsehtml(htmltemplate=htmlfile, outputdir=outputdir,
+                  outputhtml=_DOKUMENTPROSTEPOWT, d=d)
+        outfile = os.path.join(outputdir, _DOKUMENTPROSTEPOWT)
+        with open(outfile) as f:
+            xml = f.read()
+        print(xml)
+        self.assertIn("Juliusz", xml)
+        self.assertIn("Cezar", xml)
+        self.assertIn("Artyku", xml)
+        self.assertIn("999 USD", xml)
+
+    def test_proste_linie_2(self):
+        htmlfile = H.html_file(_DOKUMENTPROSTEPOWT)
+        print(htmlfile)
+        outputdir = H.tmpdir()
+        linie = [
+            {
+                "NAZWA": "Artykuł",
+                "KWOTA": "999 USD"
+            },
+            {
+                "NAZWA": "Rower",
+                "KWOTA": "888 USD"
+            }
+        ]
+
+        d = {
+            "linie": [{"IMIE": f"Juliusz {no}", "NAZWISKO": f"Cezar {no}", "linie": linie} for no in range(100)]
+        }
+        parsehtml(htmltemplate=htmlfile, outputdir=outputdir,
+                  outputhtml=_DOKUMENTPROSTEPOWT, d=d)
+        outfile = os.path.join(outputdir, _DOKUMENTPROSTEPOWT)
+        with open(outfile) as f:
+            xml = f.read()
+        print(xml)
+        self.assertIn("Juliusz 0", xml)
+        self.assertIn("Cezar", xml)
+        self.assertIn("Artyku", xml)
+        self.assertIn("999 USD", xml)
+        self.assertIn("Juliusz 99", xml)
+
+    def test_hello_page(self):
+        htmlfile = H.html_file(_HELLOPAGE)
+        print(htmlfile)
+        outputdir = H.tmpdir()
+        parsehtml(htmltemplate=htmlfile, outputdir=outputdir,
+                  outputhtml=_HELLOPAGE, d={})
+        # tylko test, ze się nie wywala