Saxonc 的 transform_to_file() 在循环中执行，不会转换，但会给出无意义的错误或部分输出

Question

我的转换样式表文件包含:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:output method="xml" encoding="UTF-8" indent="yes"/>
<xsl:template match="/">
<cities>
<xsl:for-each select="cities/country">
<city name="{@capital}" isCapital="true"/>
</xsl:for-each>
</cities>
</xsl:template>
</xsl:stylesheet>

我的python代码:

import os
import xml.etree.ElementTree as ET
from saxonpy import PySaxonProcessor
def main():
print('starting code...')
source_XML = '''
<data>
<country name="Denmark" capital="Copenhagen"/>
<country name="Germany" capital="Berlin"/>
<country name="France" capital="Paris"/>
</data>
'''
parentroot = ET.fromstring(source_XML)
children = list(parentroot)
# create individual raw xmls
cnt = 0
for child in children:
cnt = cnt + 1
childroot = ET.Element("cities")
childroot.append(child)
tempfile_tree = ET.ElementTree(childroot)

# tempfile = "C:\pythonProject\stackoverflow\tmp.xml"
# tempfile = "C:\gaga\tmp.xml"
# tempfile = os.path.abspath("tmp.xml")
tempfile = "tmp.xml"
transformedfile = f"output_{cnt}.xml"
with open(tempfile, 'wb') as f:
tempfile_tree.write(f, encoding='utf-8', xml_declaration=True)
try:
with PySaxonProcessor(license=False) as proc:
proc.set_cwd(os.getcwd())
xsltproc = proc.new_xslt30_processor()
xsltproc.transform_to_file(source_file=tempfile,
stylesheet_file="transformer.xsl",
output_file=transformedfile)
print(f"{transformedfile} has been created.")
except Exception as e:
print(e)
if __name__ == "__main__":
main()

我的问题

我导入了萨克森。我试图在循环中运行saxon的transform_to_file()。我无法获得转换后的输出文件。根据我为tempfile设置的内容，我得到

#   I/O error reported by XML parser processing C:pythonProjectstackoverflow░╚╒E ⌂:
#   unknown protocol: c. Caused by java.net.MalformedURLException: unknown protocol: c

或

Content is not allowed in prolog
(this is definitely not the case, I checked the tempfile with a hexeditor)

或无错误，但输出文件只包含:

# <?xml version="1.0" encoding="UTF-8"?>
# <cities/>

但也正确输出(但我不能再复制了)。

注意:我在安装python 3.10时禁用了MAX_PATH。注意:使用Pycharm与诗歌venv

Answer 1

使用SaxonC 11.3，我成功地运行了上面的python脚本，并进行了轻微的更改:

from saxonpy import PySaxonProcessor

替换为:

from saxonc import *

我得到了输出:

starting code...
output_1.xml has been created.
output_2.xml has been created.
output_3.xml has been created.

这些文件都有以下内容:

<?xml version="1.0" encoding="UTF-8"?>
<cities/>

当我解决时，我用transform_to_string替换了transform_to_file:

valueStr = xsltproc.transform_to_string(source_file=tempfile,
stylesheet_file="transformer.xsl")
#output_file=transformedfile)
print(valueStr)

这会产生正确的输出:

starting code...
source in transformFiletoString=tmp.xml stylsheet=transformer.xsl
<?xml version="1.0" encoding="UTF-8"?>
<cities>
<city name="Copenhagen" isCapital="true"/>
</cities>
output_1.xml has been created.
<?xml version="1.0" encoding="UTF-8"?>
<cities>
<city name="Berlin" isCapital="true"/>
</cities>
output_2.xml has been created.
<?xml version="1.0" encoding="UTF-8"?>
<cities>
<city name="Paris" isCapital="true"/>
</cities>
output_3.xml has been created.

Answer 2

我已经安装了SaxonC 1.2.1

我使用以下python脚本得到了正确的输出:

import os
import xml.etree.ElementTree as ET
from saxonpy import *
def main():
print('starting code...')
source_XML = '''
<data>
<country name="Denmark" capital="Copenhagen"/>
<country name="Germany" capital="Berlin"/>
<country name="France" capital="Paris"/>
</data>
'''
parentroot = ET.fromstring(source_XML)
children = list(parentroot)
# create individual raw xmls
try:
with PySaxonProcessor(license=False) as proc:
proc.set_cwd(os.getcwd())
xsltproc = proc.new_xslt30_processor()
cnt = 0
for child in children:
cnt = cnt + 1
childroot = ET.Element("cities")
childroot.append(child)
tempfile_tree = ET.ElementTree(childroot)

# tempfile = "C:\pythonProject\stackoverflow\tmp.xml"
# tempfile = "C:\gaga\tmp.xml"
# tempfile = os.path.abspath("tmp.xml")
tempfile = "tmp.xml"
transformedfile = f"output_{cnt}.xml"
with open(tempfile, 'wb') as f:
tempfile_tree.write(f, encoding='utf-8', xml_declaration=True)
xsltproc.set_property("s",tempfile)
xsltproc.transform_to_file(source_file=tempfile,
stylesheet_file="transformer.xsl",
output_file=transformedfile)
#print(valueStr)
print(f"{transformedfile} has been created.")
except Exception as e:
print(e)
if __name__ == "__main__":
main()

Answer 3

使用Apply_templates_returning_file()可以工作:

import os
import xml.etree.ElementTree as ET
from saxonpy import PySaxonProcessor
def main():
print('starting code...')
source_XML = '''
<data>
<country name="Denmark" capital="Copenhagen"/>
<country name="Germany" capital="Berlin"/>
<country name="France" capital="Paris"/>
</data>
'''
parentroot = ET.fromstring(source_XML)
children = list(parentroot)
try:
with PySaxonProcessor(license=False) as proc:
proc.set_cwd(os.getcwd())
xsltproc = proc.new_xslt30_processor()
xslt30_transformer = xsltproc.compile_stylesheet(stylesheet_file="transformer.xsl")
cnt = 0
for child in children:
cnt = cnt + 1
childroot = ET.Element("cities")
childroot.append(child)
tempfile_tree = ET.ElementTree(childroot)
tempfile = "tmp_1234567890ABCDEFGHIJKLMNOP.xml"
transformedfile = f"output_{cnt}.xml"
with open(tempfile, 'wb') as f:
tempfile_tree.write(f, xml_declaration=True)
xslt30_transformer.apply_templates_returning_file(source_file=tempfile,
output_file=transformedfile)
print(f"{transformedfile} has been created.")
except Exception as e:
print(e)
if __name__ == "__main__":
main()